Compare commits

...

570 Commits

Author SHA1 Message Date
Philipp Hagemeister
bdf7f13954 release 2016.03.06 2016-03-06 10:08:02 +01:00
Yen Chi Hsuan
0f56a4b443 [vimeo] Don't pollute std_headers
Fixes #8778
2016-03-06 17:01:05 +08:00
Sergey M․
1b5284b13f [downloader/fragment] Make speed more smooth
At the beginning of every segment there was a drop to Unknown speed due to timeslice being too small to calculate speed.
Now last speed from the previous fragment is used.
2016-03-06 05:36:52 +06:00
Sergey M․
d1e4a464cd [YoutubeDL] Carry long lines and improve readability 2016-03-06 04:32:18 +06:00
Sergey M․
ff059017c0 [YoutubeDL] Fix typo in m3u8_native fixup 2016-03-06 04:30:19 +06:00
remitamine
f22ba4bd60 update tests related to the change in youtube http format sorting
the change was done in 82156fdbf0
2016-03-05 21:52:24 +01:00
remitamine
1db772673e [cinemassacre] update tests 2016-03-05 21:34:34 +01:00
remitamine
75313f2baa [cnet] fix info extraction 2016-03-05 21:10:00 +01:00
remitamine
090eb8e25f Merge pull request #8718 from remitamine/m3u8-fixup
Add fixup for media files produced by HlsNative downloader(fixes #4776)
2016-03-05 18:37:28 +01:00
remitamine
a9793f58a1 Merge pull request #8754 from remitamine/5min
update 5min related web sites info extraction and add support for Aol features.
2016-03-05 18:35:48 +01:00
remitamine
7177fd24f8 [vgtv] support ap.vgtv.no and fix old videos extraction(fixes #8719) 2016-03-05 17:51:46 +01:00
Sergey M․
1e501f6c40 [jeuxvideo] Fix config URL extraction (Closes #8774) 2016-03-05 21:01:43 +06:00
remitamine
2629a3802c [revison3] fix video_id for --download-archive 2016-03-05 15:42:15 +01:00
Sergey M․
51ce91174b [YoutubeDL] Fix resolution with missing height in output template dict 2016-03-05 19:38:58 +06:00
remitamine
107d0c421a [revision3] add support for pages of type tag 2016-03-05 13:43:29 +01:00
remitamine
18b0b23992 [revision3] add support pages of type embed 2016-03-05 12:14:48 +01:00
Sergey M․
d1b29d1342 [elpais] Add support for alternative layout (Closes #8744) 2016-03-05 16:43:29 +06:00
Yen Chi Hsuan
845817aadf [twitter] Provide more metadata 2016-03-05 18:14:58 +08:00
Jaime Marquínez Ferrándiz
3233a68fbb [utils] update_url_query: Encode the strings in the query dict
The test case with {'test': '第二行тест'} was failing on python 2 (the non-ascii characters were replaced with '?').
2016-03-04 22:18:40 +01:00
remitamine
cf074e5ddd [foxnews] update test 2016-03-04 21:42:04 +01:00
Sergey M․
002c755248 [youporn] Fix sources regex 2016-03-05 01:51:27 +06:00
Sergey M․
d627cec608 [youporn] Fix quality extraction (Closes #8758) 2016-03-05 01:50:12 +06:00
remitamine
1315224cbb [bleacherreport] update tests 2016-03-04 20:14:09 +01:00
remitamine
7760b9ff4d [audimedia] update _VALID_URL and video_id regex and improve http format_id 2016-03-04 17:55:50 +01:00
Yen Chi Hsuan
28559564b2 [kusi] Correct test_KUSI 2016-03-05 00:04:29 +08:00
Yen Chi Hsuan
fa880d20ad [kusi] Two fixes
Thanks @dstftw for pointing out those
2016-03-04 23:59:58 +08:00
Sergey M․
ae7d31af1c [yandexmusic] Capture and output API errors 2016-03-04 21:32:54 +06:00
Yen Chi Hsuan
9d303bf29b Merge branch 'mutantmonkey-kusi' 2016-03-04 23:21:24 +08:00
Yen Chi Hsuan
5f1688f271 [kusi] Simplify and improve 2016-03-04 23:08:47 +08:00
remitamine
1d4c9ed90c [aol] imporve extraction
- add support for aol features
- remove support for legacy urls
2016-03-04 10:42:58 +01:00
remitamine
d48352fb5d [engadget] remove support for legacy urls 2016-03-04 10:40:39 +01:00
remitamine
6d6536acb2 [fivemin] improve extraction
- skip m3u8 formats(404 error)
- skip unavailable test
- download embed page only when it's needed
- update _VALID_URL regex(joystiq.com redirect to engadget.com)
2016-03-04 10:25:16 +01:00
Yen Chi Hsuan
b6f94d81ea [kusi] Add a test for the alternative form of URL 2016-03-04 14:32:01 +08:00
Yen Chi Hsuan
8477a69283 Merge branch 'kusi' of https://github.com/mutantmonkey/youtube-dl into mutantmonkey-kusi 2016-03-04 14:21:23 +08:00
Yen Chi Hsuan
d58cb3ec7e [leeco] Skip an invalid test. test_LePlaylist_1 is sufficient 2016-03-04 13:46:38 +08:00
Yen Chi Hsuan
8a370aedac [leeco] format_id should be strings 2016-03-04 13:38:45 +08:00
Yen Chi Hsuan
24ca0e9c0b [douyutv] Fix tests 2016-03-04 13:36:29 +08:00
Sergey M․
e1dd521e49 [livestream] Fix FutureWarning (Closes #8742) 2016-03-04 01:16:58 +06:00
remitamine
1255733945 Merge pull request #8739 from remitamine/update_url_params
[utils] add update_url_query function to create or update query string params
2016-03-03 19:24:04 +01:00
remitamine
3201a67f61 [test/test_utils] add more tests for update_url_query 2016-03-03 19:18:57 +01:00
Sergey M․
d0ff690d68 [indavideo:embed] Fix tags extraction (Closes #8738) 2016-03-04 00:09:40 +06:00
remitamine
fb640d0a3d [test/test_utils] add tests for update_url_query 2016-03-03 18:40:05 +01:00
remitamine
38f9ef31dc [utils] add update_url_query function 2016-03-03 18:34:52 +01:00
Sergey M․
a8276b2680 [twitch:playlistbase] Fix all at once fetch 2016-03-03 22:18:32 +06:00
Sergey M․
ececca6cde [twitch:playlistbase] Restore original _PAGE_LIMIT 2016-03-03 22:12:55 +06:00
Sergey M․
8bbb4b56ee [twitch:playlistsbase] Use orderedSet 2016-03-03 22:11:26 +06:00
Sergey M․
539a1641c6 [twitch] Workaround broken paging (Closes #8740) 2016-03-03 22:10:36 +06:00
Yen Chi Hsuan
1b0635aba3 [Makefile] Allow specifying the Python version in offline tests 2016-03-03 21:57:49 +08:00
Yen Chi Hsuan
429491f531 [test/http] Fix failure in Jython
make offlinetest passed on the latest Jython hg version with patched
lib-python/2.7/urllib2.py pulled from CPython 2.7.11
2016-03-03 21:55:17 +08:00
Yen Chi Hsuan
e9c0cdd389 [jython] Introduce compat_os_name
os.name is always 'java' on Jython
2016-03-03 19:24:24 +08:00
Yen Chi Hsuan
0cae023b24 Merge branch 'jython-support'
Closes #8302
2016-03-03 18:49:32 +08:00
Yen Chi Hsuan
8ee239e921 [utils] Jython support - handle filenames correctly
Now test:youtube downloads
2016-03-03 18:47:54 +08:00
remitamine
fa9e259fd9 [extractor/common] use compat_parse_qs in update_url_params 2016-03-03 10:54:39 +01:00
remitamine
f3bdae76de [extractor/common] add update_url_params helper method to add or update query string params 2016-03-03 10:27:22 +01:00
Yen Chi Hsuan
03879ff054 [twitter] Media info is not always in the first entity
Fixes #8704
2016-03-03 14:42:49 +08:00
Yen Chi Hsuan
c8398a9b87 [twitter] Now Twitter serves the same file for Firefox and Chrome 2016-03-03 14:27:27 +08:00
Yen Chi Hsuan
b8972bd69d [twitter] Fix extraction of test_Twitter and test_Twitter_1 2016-03-03 14:24:24 +08:00
Yen Chi Hsuan
0ae937a798 [twitter] Support twitter.com/i/videos/tweet/ URLS
Closes #8737
2016-03-03 13:43:45 +08:00
remitamine
4459bef203 [thepltform] detect other types of errors 2016-03-02 21:41:29 +01:00
remitamine
e07237f640 [utils] remove check for val from find_xpath_attr 2016-03-02 21:40:21 +01:00
Yen Chi Hsuan
8c5a994424 [leeco] Letv renamed to LeEco
LeEco is the company name and Le is the domain name.

For more information see the Chinese news post
http://www.techorz.com/company-news/letv-renamed-to-leeco-and-new-logo/
2016-03-03 03:27:55 +08:00
Yen Chi Hsuan
2eb25b256b [letv] Merge LetvTvIE into LetvPlaylistIE
And
1. Add more URL examples
2. Improve the matching pattern
2016-03-03 03:27:55 +08:00
Yen Chi Hsuan
f3bc19a989 [letv] Correct regular expressions and fix a typo 2016-03-03 03:27:55 +08:00
Yen Chi Hsuan
7a8fef3173 [letv] Order imports alphabetically 2016-03-03 03:27:55 +08:00
Yen Chi Hsuan
7465e7e42d [letv] Keep videos' order in playlists 2016-03-03 03:27:55 +08:00
Yen Chi Hsuan
5e73a67d44 [letv] Domain name changed 2016-03-03 03:27:55 +08:00
Sergey M․
2316dc2b9a [twitch:playlistbase] Mark broken
Twitch paging mechanism is completely broken on twitch side serving all videos all the time and making our travis builds stall.
2016-03-03 00:41:36 +06:00
Sergey M․
a2d7797cee [vimeo] Extract uploader_url (Closes #8727) 2016-03-03 00:00:11 +06:00
Sergey M․
fd050249af [youtube] Extract uploader_url (Closes #8724) 2016-03-02 23:49:10 +06:00
Sergey M․
7bcd2830dd [extractor/common] Document uploader_url 2016-03-02 23:31:24 +06:00
Sergey M
47462a125b [README.md] Document license field for output template 2016-03-02 23:10:01 +06:00
Sergey M․
7caf9830b0 [youtube] Extract license (Closes #8725) 2016-03-02 23:07:25 +06:00
Sergey M․
2bc0c46f98 [extractor/common] Document license metafield 2016-03-02 23:06:39 +06:00
remitamine
3318832e9d [youtube] improve width and height extraction from fmt_list 2016-03-02 17:52:13 +01:00
remitamine
e7d2084568 Merge branch 'master' of github.com:rg3/youtube-dl 2016-03-02 17:35:55 +01:00
remitamine
c2d3cb4c63 Revert "[youtube] add tbr to _formats extracted from watch_as3.swf"
This reverts commit 4a5ba28a87.
2016-03-02 17:35:04 +01:00
remitamine
c48dd4400f Revert "[youtube] add basic info for some unknown formats extracted from watch_as3.swf"
This reverts commit 85ca019d96.
2016-03-02 17:34:56 +01:00
Sergey M․
e38cafe986 [YoutubeDL] Skip postprocessing and archive report when outputting to stdout (Closes #8729) 2016-03-02 21:11:18 +06:00
remitamine
85ca019d96 [youtube] add basic info for some unknown formats extracted from watch_as3.swf 2016-03-02 16:05:05 +01:00
remitamine
4a5ba28a87 [youtube] add tbr to _formats extracted from watch_as3.swf 2016-03-02 16:05:05 +01:00
remitamine
82156fdbf0 [youtube] extract width and height from fmt_list 2016-03-02 16:05:05 +01:00
Sergey M․
6114090418 [nrk:skole] Relax _VALID_URL 2016-03-02 20:57:04 +06:00
Sergey M․
3099b31276 [nrk:skole] Add extractor (Closes #8728) 2016-03-02 20:52:06 +06:00
remitamine
f17f86513e Add fixup for media files produced by HlsNative downloader(fixes #4776) 2016-03-01 21:10:41 +01:00
Sergey M․
90f794c6c3 [options] Add --no-mark-watched (#5054) 2016-03-01 23:41:23 +06:00
Sergey M․
66ca2cfddd [wistia] Fix extraction (Closes #8707) 2016-03-01 23:26:53 +06:00
Sergey M
269dd2c6a7 Merge pull request #8703 from dstftw/mark-watched
Add --mark-watched feature (Closes #5054)
2016-03-01 23:00:51 +06:00
Sergey M․
e7998f59aa [lifenews] Fix extraction and improve (Closes #2482, closes #8714) 2016-03-01 22:59:11 +06:00
Yen Chi Hsuan
9fb556eef0 [iqiyi] SWF URLs are not used anymore
Since automatic detection of enc_key failed

Closes #8705
2016-03-01 08:42:33 +08:00
Philipp Hagemeister
e781ab63db release 2016.03.01 2016-03-01 00:05:39 +01:00
Jaime Marquínez Ferrándiz
3e76968220 [rtve.es:live] Fix extraction
* Update _VALID_URL to match the current URLs
* Use the m3u8 manifest since I haven't figured out how to use the rtmp stream
2016-02-29 20:57:26 +01:00
Sergey M․
2812c24c16 [mdr] Fix extraction (Closes #8702) 2016-03-01 01:24:26 +06:00
Sergey M․
d77ab8e255 Add --mark-watched feature (Closes #5054) 2016-03-01 01:01:33 +06:00
Sergey M․
4b3cd7316c [tf1] Improve wat id regex (Closes #8691) 2016-02-29 03:28:21 +06:00
Sergey M․
6dae56384a [screenwavemedia] Check formats' URLs 2016-02-28 21:46:36 +06:00
Sergey M․
2b2dfae83e [screenwavemedia] Improve formats sorting 2016-02-28 20:16:31 +06:00
Sergey M․
6c10dbeae9 [screenwavemedia] Improve formats extraction 2016-02-28 20:05:58 +06:00
Jaime Marquínez Ferrándiz
9173202b84 [zdf] Ignore hls manifests that use https (closes #8665)
The certificates are misconfigured, you get the following error mesage:

    ssl.CertificateError: hostname u'zdf-hdios-none-i.zdf.de' doesn't match either of 'a248.e.akamai.net', '*.akamaihd.net', '*.akamaihd-staging.net', '*.akamaized.net', '*.akamaized-staging.net'
2016-02-28 14:06:26 +01:00
Sergey M․
8870bb4653 [webofstories] Tolerate malforder og:title (Closes #8417) 2016-02-28 03:37:48 +06:00
Sergey M
7a0e7779fe [README.md] Use simple wording instead of env variable for home 2016-02-28 03:12:13 +06:00
Sergey M
a048ffc9b0 [README.md] Clarify configuration file options syntax 2016-02-28 03:04:06 +06:00
Sergey M
4587915b2a [README.md] Make configuration file example more diverse 2016-02-28 02:56:09 +06:00
Philipp Hagemeister
da665ddc25 release 2016.02.27 2016-02-27 21:31:21 +01:00
Sergey M․
5add979d91 [dplay] Add support for dplay.no 2016-02-27 21:42:08 +06:00
Sergey M․
20afe8bd14 Credit @aidan- for more dplay sites support (#8463) 2016-02-27 21:31:43 +06:00
Sergey M․
940b606a07 [dplay] Improve, extract all formats and metadata (Closes #8463) 2016-02-27 21:30:47 +06:00
Aidan Rowe
9505053704 [dplay] add support for it.dplay.com and dplay.dk 2016-02-27 19:40:36 +06:00
Sergey M․
2c9ca78281 [extractor/generic] Add support for tnaflix network embeds (Closes #7505) 2016-02-27 17:15:49 +06:00
Sergey M․
63719a8ac3 [tnaflixnetwork:embed] Add _extract_urls 2016-02-27 17:15:06 +06:00
Sergey M․
8fab62482a [tnaflixnetwork] Fallback age limit to 18 2016-02-27 16:59:10 +06:00
Sergey M․
d6e9c2706f [tnaflixnetwork:embed] Add extractor 2016-02-27 16:58:11 +06:00
Sergey M․
f7f2e53a0a [imdb] Recognize 1080p formats (Closes #8677) 2016-02-27 15:51:25 +06:00
Sergey M․
9cdffeeb3f [extractor/common] Clarify rationale on media playlist detection 2016-02-27 07:01:11 +06:00
Sergey M․
fbb6edd298 [extractor/common] Properly extract audio only formats in master m3u8 playlists 2016-02-27 06:48:13 +06:00
Yen Chi Hsuan
5eb6bdced4 [utils] Multiple changes to base_n()
1. Renamed to encode_base_n()
2. Allow tables longer than 62 characters
3. Raise ValueError instead of AssertionError for invalid input data
4. Return the first character in the table instead of '0' for number 0
5. Add tests
2016-02-27 03:22:52 +08:00
Yen Chi Hsuan
5633b4d39d [infoq] Use BokeCC extractor function 2016-02-27 02:55:11 +08:00
Yen Chi Hsuan
4435c6e98e [bokecc] Add new extractor (#2336) 2016-02-27 02:54:43 +08:00
Yen Chi Hsuan
2ebd2eac88 [letv] Speedup M3U8 decryption 2016-02-27 00:58:03 +08:00
Sergey M․
b78b292f0c [youtube] Add alternative automatic captions extraction approach (Closes #8667) 2016-02-26 22:21:47 +06:00
Yen Chi Hsuan
efbd6fb8bb [vidzi] Use decode_packed_codes
Javascript codes found on Vidzi are slightly different from those found
in VideoMega and iQiyi. Nevertheless, the difference has no effects on
the final result.
2016-02-26 15:14:13 +08:00
Yen Chi Hsuan
680079be39 [utils] Relaxing regex in decode_packed_codes for vidzi 2016-02-26 15:13:03 +08:00
Yen Chi Hsuan
e4fc8d2ebe [videomega] Fix extraction (closes #7606) 2016-02-26 15:00:48 +08:00
Yen Chi Hsuan
f52354a889 [utils] Move codes for handling eval() from iqiyi.py 2016-02-26 14:58:29 +08:00
Yen Chi Hsuan
59f898b7a7 [utils] Merge base_n functions 2016-02-26 14:37:20 +08:00
Yen Chi Hsuan
8f4a2124a9 [vidzi] Fix extraction 2016-02-26 14:26:26 +08:00
Yen Chi Hsuan
481888294d [utils] Add base36 for use in Vidzi 2016-02-26 14:26:26 +08:00
Yen Chi Hsuan
d1e440a4a1 [jwplatform] Separate codes for for parsing jwplayer data 2016-02-26 14:26:26 +08:00
Yen Chi Hsuan
81bdc8fdf6 [utils] Move base62 to utils 2016-02-26 14:26:26 +08:00
Yen Chi Hsuan
e048d87fc9 [kuwo] Fix a test 2016-02-26 14:26:26 +08:00
Sergey M․
e26cde0927 [space] Remove extractor (Closes #8662)
Now uses ooyala embed
2016-02-25 21:46:43 +06:00
Sergey M․
20108c6b90 [ustudio] Improve (Closes #8574) 2016-02-25 21:30:19 +06:00
mutantmonkey
9195ef745a [uStudio] Add new extractor 2016-02-25 21:29:49 +06:00
Sergey M․
d0459c530d [motherless] Update tests 2016-02-25 00:54:41 +06:00
Sergey M․
f160785c5c [utils] Remove AM/PM from unified_strdate patterns 2016-02-25 00:52:49 +06:00
Sergey M․
5c0a57185c [motherless] Detect non-existing videos 2016-02-25 00:42:19 +06:00
Sergey M․
43479d9e9d [motherless] Make categories optional (Closes #8654) 2016-02-25 00:36:14 +06:00
Sergey M
c0da50d2b2 [README.md] Turn references to issues to links 2016-02-24 23:05:23 +06:00
Yen Chi Hsuan
c24883a1c0 [facebook] Fix format sorting
'hd' formats should have higher priorities
2016-02-24 03:43:24 +08:00
Yen Chi Hsuan
1b77ee6248 [c56] Support videos hosted on Sohu (closes #8073) 2016-02-24 03:32:29 +08:00
Sergey M․
bf4b3b6bd9 [vk] Extract video URL from extra_data (Closes #8646) 2016-02-23 18:47:13 +06:00
Yen Chi Hsuan
efbeddead3 [facebook] Support mobile URLs (closes #8638) 2016-02-23 13:17:24 +08:00
Yen Chi Hsuan
3cfeb1624a [nba] Support channels (#5362, #4167) 2016-02-23 13:11:20 +08:00
Yen Chi Hsuan
b95dc034ca [utils] Implement cache for OnDemandPagedList 2016-02-23 13:11:20 +08:00
Yen Chi Hsuan
86a7dbe66e [nba] Support non-video/ pages
Fixes #8589
2016-02-23 13:11:20 +08:00
Sergey M
b43a7a92cd [README.md] Fix typo 2016-02-23 05:41:09 +06:00
Sergey M
6563d31710 [README.md] Fix typo 2016-02-23 05:37:49 +06:00
Sergey M
cf89ba9eff [README.md] Clarify robustness and future-proof requirements for new extractors 2016-02-23 05:35:19 +06:00
Sergey M
9b01272832 [README.md] Update link to extractor metafields 2016-02-23 05:03:57 +06:00
Sergey M
58525c94d5 [README.md] Emphasize copyright infringement aspects in add-new-site-support tutorial 2016-02-23 04:58:51 +06:00
Sergey M
621bd0cda9 [README.md] Add tl;dr links to examples 2016-02-23 04:43:45 +06:00
Sergey M
1610f770d7 [README.md] Extract example subsections 2016-02-23 04:29:39 +06:00
Sergey M
0fc871d2f0 [README.md:output_template] Add example for channel/user playlists download 2016-02-23 04:16:47 +06:00
Sergey M․
1ad6143061 [xfileshare] Add support for powerwatch (Closes #8628) 2016-02-22 17:37:00 +06:00
Philipp Hagemeister
92da3cd848 release 2016.02.22 2016-02-22 11:57:31 +01:00
remitamine
6212bcb191 [tf1] fix info extraction(fixes #8599) 2016-02-22 09:57:40 +01:00
Sergey M․
d69abbd3f0 [googledrive] Make thumbnail optional (Closes #8629) 2016-02-22 03:13:18 +06:00
Sergey M․
1d00a8823e [arte] PEP 8 2016-02-22 01:32:23 +06:00
Sergey M․
5d6e1011df [pbs] Extract all formats (Closes #8538) 2016-02-22 01:23:27 +06:00
Sergey M․
f5bdb44443 [extractor/common] Add _remove_duplicate_formats 2016-02-22 01:19:39 +06:00
Yen Chi Hsuan
7efc1c2b49 [twitter] Fix metadata extraction and test_Twitter_1 2016-02-21 17:29:28 +08:00
Yen Chi Hsuan
132e3b74bd [twitter] Fix a typo 2016-02-21 17:21:37 +08:00
Yen Chi Hsuan
bdbf4ba40e [twitter:amplify] Extract more metadata 2016-02-21 17:16:35 +08:00
Yen Chi Hsuan
acb6e97e6a [twitter] Fix several failed tests 2016-02-21 16:57:56 +08:00
Yen Chi Hsuan
445d72b8b5 [twitter:amplify] Add TwitterAmplifyIE for handling Twitter smart URLs
Closes #8075
2016-02-21 16:41:24 +08:00
Sergey M․
92c5e11b40 [arte:future] Fix test 2016-02-21 14:23:58 +06:00
Sergey M․
0dd046c16c [arte:magazine] Fix test 2016-02-21 13:57:30 +06:00
Sergey M․
305168ca3e [arte:+7] Detect more embeds (Closes #8613) 2016-02-21 13:55:25 +06:00
Sergey M․
b72f6163dc [arte:+7] Improve _VALID_URL 2016-02-21 13:37:31 +06:00
Sergey M․
33d4fdabfa [extractor/generic] Add support for ok embeds (#8619) 2016-02-21 09:51:54 +06:00
remitamine
cafcf657a4 add more subtitles mime types to mimetype2ext and fix the platform subtitle extraction 2016-02-20 22:02:03 +01:00
Yen Chi Hsuan
101067de12 Jython support - handle *.class files 2016-02-21 03:32:03 +08:00
Yen Chi Hsuan
7360db05b4 [postprocessor/embedthumbnail] Allow mkv to embed thumbnails
Fixes #6046
2016-02-21 03:32:03 +08:00
Yen Chi Hsuan
c1c05c67ea [utils] Jython support - disable setproctitle() until ctypes is complete 2016-02-21 03:32:03 +08:00
Yen Chi Hsuan
399a76e67b [utils] Jython support: tolerate missing fcntl module 2016-02-21 03:32:03 +08:00
Jaime Marquínez Ferrándiz
765ac263db [utils] mimetype2ext: return 'm4a' for 'audio/mp4' (fixes #8620)
The youtube extractor was using 'mp4' for them, therefore filters like 'bestaudio[ext=m4a]' stopped working (94278f7202 broke it).
2016-02-20 19:55:10 +01:00
Yen Chi Hsuan
a4e4d7dfcd [test_iqiyi_sdk_interpreter] Add test for iQiyi login 2016-02-20 23:10:39 +08:00
Yen Chi Hsuan
73f9c2867d [iqiyi] Support playlists (closes #8019) 2016-02-20 22:44:04 +08:00
Philipp Hagemeister
9c86d50916 [faz] Future-proof XML element check 2016-02-20 14:11:44 +01:00
Yen Chi Hsuan
1d14c75f55 [Makefile] iQiyi login test requires network 2016-02-20 20:49:30 +08:00
Yen Chi Hsuan
99709cc3f1 [iqiyi] Implement _login()
Currently only email login supported
2016-02-20 19:54:58 +08:00
Yen Chi Hsuan
5bc880b988 [utils] Add OHDave's RSA encryption function 2016-02-20 19:54:58 +08:00
Yen Chi Hsuan
958759f44b [appletrailers] Extend _VALID_URL (#8524) 2016-02-20 15:54:00 +08:00
Sergey M․
86bf29050e [test_YoutubeDL] Make test pass until more intelligent sort formats (Closes #8462) 2016-02-20 03:36:03 +06:00
remitamine
04cbc4980d [mtv] imporove duration extraction 2016-02-19 20:56:45 +01:00
RiCON
8765151c8a [mtv] Extract duration from each playlist item
RSS used instead of manifest files because it's exact to the millisecond
with the video I tested while in manifest it's only exact to the second.
2016-02-19 19:38:28 +00:00
Sergey M
8ec64ac683 [README.md] Clarify verbose log 2016-02-19 22:18:21 +06:00
Sergey M․
ed8648a322 [pornhub] Fix thumbnail and duration extraction (Closes #8604) 2016-02-19 21:42:46 +06:00
Sergey M․
88641243ab [pornhub:playlistbase] Improve extract entries 2016-02-18 22:30:19 +06:00
Sergey M․
40e146aa1e [pornhub:user:videos] Add extractor (Closes #8548) 2016-02-18 22:29:17 +06:00
Sergey M․
f3f9cd9234 [francetv] Improve video id regex (Closes #8563) 2016-02-18 22:09:21 +06:00
Sergey M․
ebf1b291d0 [youtube:watchlater] Respect --no-playlist 2016-02-18 22:03:46 +06:00
Sergey M․
bc7a9cd8fb [youtube:watchlater] Improve _VALID_URL (Closes #8594) 2016-02-18 21:50:21 +06:00
Sergey M․
d48502b82a [arte] Improve _VALID_URLs 2016-02-18 21:29:52 +06:00
Sergey M․
479ec54a8d [arte:magazine] Improve (Closes #8473) 2016-02-18 21:29:07 +06:00
Thomas Jost
49625662a9 [arte:magazine] Add extractor 2016-02-18 21:28:18 +06:00
remitamine
8b809a079a [cbsnews] use find_xpath_attr 2016-02-18 16:10:09 +01:00
remitamine
778433cb90 [cbsnews] extract subtitle url from theplatform SMIL manifest(fixes #8568) 2016-02-18 15:43:28 +01:00
cazulu
411cb8f476 [dailymotion] Fix view count extraction
Fix view count parsing when the decimal marker is a whitespace, e.g. '101 101'
2016-02-18 20:31:43 +06:00
Sergey M․
63bf4f0dc0 [vrt] Detect geo restriction 2016-02-17 23:28:41 +06:00
Sergey M․
80e59a0d5d [vrt] Make formats extraction non fatal (Closes #8587) 2016-02-17 23:18:23 +06:00
Sergey M․
8bbd3d1476 [arte] Fix upload date extraction (Closes #8581) 2016-02-17 22:51:08 +06:00
Sergey M․
e725e4bced [arte] PEP 8 2016-02-17 22:37:55 +06:00
Sergey M․
08d65046f0 [arte] Make sorting aware of en/es formats 2016-02-17 22:37:05 +06:00
Sergey M․
44b9745000 [arte] Extend more _VALID_URLs for en and es support 2016-02-17 21:53:53 +06:00
Sergey M․
9654fc875b [arte:+7] Fix extraction for react-based layout 2016-02-17 21:49:15 +06:00
Sergey M․
0f425e65ec [arte:+7] Add support for en and es URLs 2016-02-17 21:47:18 +06:00
mutantmonkey
199e724291 [KUSI] Add new extractor 2016-02-16 19:55:46 -08:00
Sergey M․
e277f2a63b [orf:tvthek] Check formats (Closes #8580) 2016-02-16 22:23:38 +06:00
Sergey M․
f4db09178a [xtube:user] Remove duplicated video ids 2016-02-16 22:06:26 +06:00
Sergey M․
86be3cdc2a [xtube] Fix extraction (Closes #8565) 2016-02-16 22:05:23 +06:00
Yen Chi Hsuan
cb64ccc715 [facebook] Improve error handling (#8572) 2016-02-16 09:07:38 +08:00
Sergey M․
f66a3c7bc2 [screenjunkies] Fix spelling 2016-02-16 01:30:00 +06:00
Sergey M․
fe80df3080 Credit @TingPing for screenjunkies (#8505) 2016-02-16 01:24:57 +06:00
Yen Chi Hsuan
1932476c13 [iqiyi] Omit MD5 sums for the VIP-only video 2016-02-16 02:45:21 +08:00
Sergey M․
d2c1f79f20 [youtube:searchurl] Extend _VALID_URL 2016-02-16 00:29:51 +06:00
Sergey M․
8eacae8cf9 Credit @RobinHoutevelts for canvas subtiltes (#8537) 2016-02-15 22:33:32 +06:00
Sergey M․
c8a80fd818 [screenjunkies] Improve, extract more metadata and workaround subscription (Closes #8505) 2016-02-15 22:29:28 +06:00
Patrick Griffis
b9e8d7140a [screenjunkies] Add new extractor
This doesn't handle the plus only videos yet

Closes #8492
2016-02-15 22:28:36 +06:00
Sergey M․
6eff2605d6 [canvas] Add subtitles test (#8537) 2016-02-15 20:59:16 +06:00
Sergey M․
fd7a3ea4a4 [canvas] Improve subtitles (Closes #8537) 2016-02-15 20:54:01 +06:00
Robin Houtevelts
8d3eeb36d7 [Canvas] Add subtitles 2016-02-15 20:50:03 +06:00
Yen Chi Hsuan
8e0548e180 [iqiyi] Partial support for VIP-only videos
See #8569 and #8019. Currently only 6-min preview are supported
2016-02-15 19:58:24 +08:00
Philipp Hagemeister
a517bb4b1e [noz] Add new extractor 2016-02-15 00:07:16 +01:00
Sergey M․
9dcefb23a1 [laola1tv] Improve (Closes #8478) 2016-02-14 23:40:26 +06:00
Sergey M․
d9da74bc06 Credit @blackwinter for laola1tv (#8478) 2016-02-14 23:39:49 +06:00
Jens Wille
5e19323ed9 [laola1tv] Fixes for changed site layout.
* Fixed valid URLs (w/ tests).
* Fixed iframe URL extraction.
* Fixed token URL extraction.
* Fixed variable extraction.
* Fixed uploader spelling.
* Added upload_date to result dictionary.
2016-02-14 23:01:49 +06:00
Sergey M․
611c1dd96e [refactor] Single quotes consistency 2016-02-14 15:37:17 +06:00
Sergey M․
d800609c62 [refactor] Do not specify redundant None as second argument in dict.get() 2016-02-14 14:25:04 +06:00
Sergey M․
c78c9cd10d [downloader/dash] PEP 8 2016-02-14 14:13:09 +06:00
Sergey M․
e76394f36c [globo] Switch to new-style classes 2016-02-14 14:02:12 +06:00
Sergey M․
080e09557d [aes] Switch to new-style classes 2016-02-14 14:01:43 +06:00
Sergey M․
fca2e6d5a6 [dailymotion:cloud] Use idiomatic name for classmethod's first argument 2016-02-14 13:44:23 +06:00
Sergey M․
b45f2b1d6e [myvideo] Mark broken 2016-02-14 11:24:57 +06:00
remitamine
fc2e70ee90 Merge pull request #8479 from remitamine/dash_downloader
[downloader/dash] Implement dashsegments fd in terms of fragment fd
2016-02-13 21:12:33 +01:00
Sergey M․
b4561e857f [animeondemand] Add .netrc 2016-02-13 22:41:58 +06:00
Jaime Marquínez Ferrándiz
7023251239 [comedycentral] Support /shows URLs (fixes #8405) 2016-02-13 12:26:27 +01:00
Sergey M․
e2bd68c901 [animeondemand][wip] Add extractor (#8518) 2016-02-13 13:30:31 +06:00
Philipp Hagemeister
35ced3985a release 2016.02.13 2016-02-13 08:25:05 +01:00
Sergey M․
3e18700d45 [nbc] Correct test 2016-02-13 07:45:32 +06:00
Sergey M․
f9f49d87c2 [youtube] Add test for #8536 2016-02-13 05:18:58 +06:00
Sergey M․
6863631c26 [youtube] Improve multifeed videos extraction (Closes #8536) 2016-02-13 05:01:20 +06:00
Sergey M․
9d939cec48 [extractor/generic] Add direct mpd url test 2016-02-13 00:36:47 +06:00
Sergey M․
4c77d3f52a [YoutubeDL] Allow bestvideo+bestaudio for any extractor 2016-02-13 00:23:14 +06:00
Sergey M․
7be747b921 [extractor/generic] Pass mpd base url to _parse_mpd_formats 2016-02-13 00:15:59 +06:00
Sergey M․
bb20526b64 [extractor/common] Improve base url construction 2016-02-13 00:13:56 +06:00
remitamine
bcbb1b08b2 Revert "[aenetworks] extract http formats"
This reverts commit 3d98f97c64.
2016-02-12 17:56:06 +01:00
remitamine
3d98f97c64 [aenetworks] extract http formats 2016-02-12 17:39:32 +01:00
remitamine
c349456ef6 [extractor/common] strip http urls in smil manifest 2016-02-12 17:38:48 +01:00
Sergey M․
5a4905924d [extractor/generic] Improve dailymotion embed detection (Closes #8521, closes #8325) 2016-02-12 22:03:10 +06:00
Sergey M․
b826035dd5 [vimeo] Fix authentication (Closes #8520) 2016-02-12 03:16:26 +06:00
remitamine
a7cab4d039 [theplatform] remove unused import and change smil url for ThePlatformFeedIE 2016-02-11 18:50:14 +01:00
remitamine
fc3810f6d1 Merge branch 'master' of github.com:rg3/youtube-dl 2016-02-11 18:13:56 +01:00
remitamine
3dc71d82ce [theplatform] fix pid extraction in the platform feed 2016-02-11 18:13:03 +01:00
Sergey M․
9c7b38981c [utils] Bump Firefox version in User-Agent
Old version number causes Youtube not to serve some formats in ytplayer.config
2016-02-11 23:12:30 +06:00
remitamine
8b85ac3fd9 [cbc] Add new extractor(closes #3803)(closes #4731)(closes #5309) 2016-02-11 18:10:32 +01:00
remitamine
81e1c4e2fc [extractor/common] remove duplicate rtmp formats in smil manifest 2016-02-11 17:58:48 +01:00
Sergey M․
388ae76b52 [YoutubeDL] Fix format resolution when height is missing 2016-02-11 22:46:13 +06:00
Sergey M․
b67d63149d [youtube] Fix typos 2016-02-11 22:33:08 +06:00
Sergey M․
28280e8ded [plays] PEP 8 2016-02-11 22:02:57 +06:00
Sergey M․
6b3fbd3425 [pbs] Fix multi part videos extraction 2016-02-11 22:02:37 +06:00
Sergey M․
a7ab46375b [pbs] Update some tests 2016-02-11 21:43:01 +06:00
Sergey M․
b14d5e26f6 [pbs] Improve description extraction 2016-02-11 21:28:09 +06:00
Sergey M․
9a61dfba0c [pbs] Revert prefer portalplayer 2016-02-11 21:22:57 +06:00
remitamine
154c209e2d [extractor/common] improve dash format ids 2016-02-11 10:33:26 +01:00
remitamine
d1ea5e171f [plays] Add new extractor(#8458) 2016-02-11 10:30:31 +01:00
remitamine
a1188d0ed0 [crackle] add prefix to format ids 2016-02-10 22:39:33 +01:00
remitamine
47d205a646 [crackle] improve format sorting 2016-02-10 22:23:56 +01:00
remitamine
80f772c28a [crackle] Add new extractor 2016-02-10 22:16:21 +01:00
Philipp Hagemeister
f817d9bec1 release 2016.02.10 2016-02-10 16:17:38 +01:00
Sergey M․
e2effb08a4 [YoutubeDL] Sanitize format_id (Closes #8494) 2016-02-10 21:16:58 +06:00
Sergey M․
7fcea295c5 [pbs] Switch to portal player by default (Closes #8491) 2016-02-10 20:46:38 +06:00
Sergey M․
cc799437ea [youku] Report private videos (Closes #8498) 2016-02-10 20:05:17 +06:00
Sergey M․
89d23f37f2 [hotstar] Relax _VALID_URL (Closes #8487) 2016-02-10 04:43:00 +06:00
Philipp Hagemeister
b92071ef00 release 2016.02.09.1 2016-02-09 20:12:36 +01:00
Sergey M․
47246ae26c [viddler] Update tests 2016-02-10 01:12:47 +06:00
Sergey M․
9c15869c28 [viddler] Add support for secret videos (Closes #8481) 2016-02-10 01:09:07 +06:00
remitamine
51e9094f4a [extractor/common] extract youtube dash formats filesize(fixes #8480) 2016-02-09 20:05:39 +01:00
remitamine
5e3a6fec33 [fox] update test 2016-02-09 17:30:42 +01:00
remitamine
c43fe0268c [downloader/dash] Implement dashsegments fd in terms of fragment fd 2016-02-09 17:25:44 +01:00
remitamine
d413095f7e [extractor/common] remove duplicated formats and subtiles in smil manifests 2016-02-09 17:15:41 +01:00
remitamine
1bedf4de06 [fox] extract http formats 2016-02-09 17:12:34 +01:00
Sergey M․
3967a761f4 [mailru] Fix tests 2016-02-09 21:31:51 +06:00
Sergey M․
b081350bd9 [mailru] Improve and modernize 2016-02-09 21:30:48 +06:00
Sergey M․
16f1430ba6 [mailru] Prefer metaUrl API (Closes #8474) 2016-02-09 21:14:02 +06:00
Philipp Hagemeister
085ad71157 release 2016.02.09 2016-02-09 12:57:51 +01:00
Sergey M․
35972ba172 [vk] Improve rutube embeds detection (Closes #8461) 2016-02-08 21:30:23 +06:00
Sergey M․
3834d3e35c [youtube] Clarify itag 36 height and abr (Closes #8457) 2016-02-08 01:30:57 +06:00
Sergey M
8d0a2a2a4e [README.md] Fix typo 2016-02-07 21:23:29 +06:00
Sergey M
11c0339bec [README.md] Clarify quotes in output template 2016-02-07 21:22:33 +06:00
Sergey M
915dd77783 [README.md] Add output template example for streaming to stdout 2016-02-07 21:21:14 +06:00
Sergey M․
b6bfa6fb79 [konserthusetplay] Reorder code pieces 2016-02-07 21:18:32 +06:00
Sergey M․
f070197bd7 [konserthusetplay] Improve _VALID_URL 2016-02-07 21:16:31 +06:00
Sergey M․
5a7699bb2e [konserthusetplay] Improve and extract all formats (Closes #8381) 2016-02-07 21:11:59 +06:00
ovitei
8628d26f38 [KonserthusetPlay] Add new extractor (partial support) 2016-02-07 19:47:29 +06:00
Sergey M․
8411229bd5 [utils] Allow dot in strip_jsonp 2016-02-07 19:47:09 +06:00
Sergey M
72b9ebc65d [README.md] Document extractor sequences in output template 2016-02-07 19:08:54 +06:00
Sergey M
3b799ca14c [README.md] Clarify percent literal and output to stdout 2016-02-07 19:06:42 +06:00
Sergey M
0474512e30 [README.md] Document even more sequences in output template 2016-02-07 19:00:59 +06:00
Sergey M
f0905c6ec3 [README.md] Document more sequences in output template 2016-02-07 18:45:44 +06:00
Sergey M․
86296ad2cd [utils] Add ability to control skipping false values in dict_get 2016-02-07 08:13:04 +06:00
Sergey M․
52f5889f77 [vlive] Improve and extract more metadata (Closes #8446) 2016-02-07 06:17:40 +06:00
Sergey M․
81e0b4f2d1 Credit @EraYaN for vlive update (#8446) 2016-02-07 06:14:26 +06:00
Sergey M․
cbecc9b903 [utils] Add dict_get convenience method 2016-02-07 06:12:53 +06:00
Erwin de Haan
b8b465af3e [vlive] Updated to new V App/VLive api.
More robust with getting keys and ids from website.
2016-02-07 05:27:17 +06:00
pulpe
59b35c6745 [IPrima] Remove test video_id 2016-02-06 21:42:24 +01:00
Jaime Marquínez Ferrándiz
7032833011 [iprima] Follow pep8 2016-02-06 21:37:28 +01:00
pulpe
f406c78785 [IPrima] Fix extractor (fixes #7617) 2016-02-06 21:23:41 +01:00
Sergey M
f326b5837a Merge pull request #8445 from bpfoley/rte-newurl
[rte:radio] Add support for RTMP downloads, alternate URL style
2016-02-07 00:28:39 +05:00
Brian Foley
5dd4b3468f [rte:radio] Add support for RTMP downloads, alternate URL style
This is useful as
a) RTMP downloads are a good deal faster to download
b) Older items are available only as RTMP streams
2016-02-06 18:42:57 +00:00
Jaime Marquínez Ferrándiz
d4f8e83404 [FFmpegSubtitlesConvertorPP] remove unused variable 2016-02-06 19:04:53 +01:00
Jaime Marquínez Ferrándiz
7b8b007cd9 [FFmpegSubtitlesConvertorPP] remove intermediate srt files 2016-02-06 19:04:18 +01:00
Jaime Marquínez Ferrándiz
3547d26587 [FFmpegSubtitlesConvertorPP] correctly update the extension (fixes #8444) 2016-02-06 18:58:18 +01:00
Jaime Marquínez Ferrándiz
7e62c2eb6d [FFmpegSubtitlesConvertorPP] fix not working when srt is used as the intermediate format between ttml/dfxp and other format
It was trying to use the ttml/dfxp file with ffmpeg, which doesn't have support for them.
I broke it in e04398e397.
2016-02-06 18:51:05 +01:00
Sergey M․
56401e1e5f [downloader/hls] Do not send 'q' to ffmpeg on Windows (Closes #8300) 2016-02-06 23:24:22 +06:00
Sergey M
860db2d508 [README.md] Fix typo 2016-02-06 22:40:20 +06:00
Sergey M
4b8874975c [README.md] Remove non-relevant info 2016-02-06 22:39:50 +06:00
Sergey M
bd6b6f6622 [README.md] Fix typo 2016-02-06 22:36:30 +06:00
Sergey M․
4340727e6c [videomore] Fix typo 2016-02-06 22:36:30 +06:00
Sergey M
3ceccade87 [README.md] Improve output template documentation and add more examples 2016-02-06 22:33:49 +06:00
remitamine
28ad7df65d [generic] detect MPD manfiest only from the content 2016-02-06 14:51:45 +01:00
Sergey M․
79a3508579 [extractor/generic] Detect DASH manifests in found URLs and extract mpd formats 2016-02-06 19:42:03 +06:00
Sergey M․
1b840245bd [extractor/generic] Detect DASH manifests and extract mpd formats 2016-02-06 19:35:32 +06:00
remitamine
6a3828fddd [common] use float conversion instead of using division from __future__ 2016-02-06 14:27:04 +01:00
remitamine
91cb6b5065 rename _parse_mpd to _parse_mpd_formats and add default value for mpd namespace 2016-02-06 14:03:48 +01:00
remitamine
0826a0b555 [common] sort dash formats 2016-02-06 06:52:48 +01:00
remitamine
bcbbb98bfe [generic] extract dash formats detected using content type 2016-02-06 06:47:38 +01:00
remitamine
66159b38aa Merge pull request #8408 from remitamine/dash
Add generic support for mpd manifests(dash formats)
2016-02-06 06:26:02 +01:00
Sergey M․
23d17e4beb [youtube] Fix automatic captions 2016-02-06 06:44:38 +06:00
Sergey M․
d97b0e3241 [vidme] Clarify IE_NAMEs 2016-02-05 23:58:26 +06:00
Sergey M․
eb2533ec4c [vidme:user:likes] Add extractor 2016-02-05 23:57:35 +06:00
Sergey M․
b7b365067f [vidme:user] Add extractor (Closes #8416) 2016-02-05 23:32:22 +06:00
remitamine
86e284e028 Merge branch 'master' of github.com:rg3/youtube-dl 2016-02-05 17:20:00 +01:00
Sergey M․
d9e543b680 [spankbang] Add test with single format (#8398) 2016-02-05 22:16:56 +06:00
Sergey M․
c773c232d8 [spankbang] Check formats (#8398) 2016-02-05 22:16:40 +06:00
Sergey M․
58ae24336a [spankbang] Extend format id regex (Closes #8398) 2016-02-05 22:16:12 +06:00
remitamine
7d3a035ee0 [ffmpeg] check for m3u8 protocol in FFmpegMetadataPP 2016-02-05 17:12:49 +01:00
Philipp Hagemeister
e06e75c7e7 release 2016.02.05.1 2016-02-05 15:17:31 +01:00
remitamine
593e0f43b4 [ffmpeg] fix condition(fixes #8440) 2016-02-05 15:12:06 +01:00
Philipp Hagemeister
008ab0f814 release 2016.02.05 2016-02-05 11:04:00 +01:00
Jaime Marquínez Ferrándiz
3f7e8750d4 [arte.tv:+7] Fix extraction (fixes #8427) 2016-02-04 20:16:47 +01:00
Philipp Hagemeister
f1ed3acae5 release 2016.02.04 2016-02-04 13:39:26 +01:00
remitamine
920d21b9d3 [test_subtitles] update youtube subtitles tests 2016-02-04 08:50:55 +01:00
remitamine
2fb35d1c28 [youtube] fix subtitle order 2016-02-04 08:39:01 +01:00
remitamine
09be85b8dd [youtube] fix subtitle extraction(fixes #8415) 2016-02-04 08:28:37 +01:00
remitamine
eadc3ccd50 [generic] extract m3u8 formats when mpegurl content type detected 2016-02-04 01:25:36 +01:00
remitamine
255732f0d3 [common] fix segment duration calculation 2016-02-03 23:57:08 +01:00
remitamine
53c269c6fd [common] fix media_template string formating 2016-02-03 23:54:34 +01:00
remitamine
675d001633 [common] skip drm protected dash formats 2016-02-03 18:44:43 +01:00
Yen Chi Hsuan
58be922079 [kuwo] Check for georestriction 2016-02-04 01:26:25 +08:00
Sergey M
c84d3a557d [README.md] Clarify unavailable sequences in output format 2016-02-03 19:18:25 +05:00
remitamine
d577c79632 [common] ignore ISO 639-2 generic codes 2016-02-03 13:24:07 +01:00
remitamine
6ad2b01e14 [srgssr] use flv as ext for rtmp formats 2016-02-02 23:09:50 +01:00
remitamine
fd3a1f3d60 [cbsnews] add support for live videos(fixes #7010) 2016-02-02 23:02:18 +01:00
Jaime Marquínez Ferrándiz
87de7069b9 [utils] dfxp2srt: make TTMLPElementParser inherit from object
For consistency between python 2 and 3.
2016-02-02 22:30:13 +01:00
remitamine
6fba62c87a [ffmpeg] fix adding metadata when using --hls-prefer-native(#8350) 2016-02-02 22:14:23 +01:00
remitamine
f14be22816 [common] remove duplicate reference to namespace 2016-02-02 22:02:08 +01:00
Yen Chi Hsuan
1df4141196 [test_YoutubeDL] Fix test_youtube_format_selection
Broken since a6c2c24479. Thanks to
@jaimeMF and @anisse for pointing that out
2016-02-03 03:42:37 +08:00
remitamine
fae45ede08 Merge pull request #8354 from remitamine/m3u8_metadata
[ffmpeg] fix adding metadata when using m3u8_native(fixes #8350)
2016-02-02 19:13:58 +01:00
remitamine
4e0cff2a50 Merge pull request #8348 from remitamine/dfxp2srt-text
[utils] fix dfxp2srt text extraction(fixes #8055)
2016-02-02 18:36:26 +01:00
remitamine
9c74423510 [common] fix media template regex 2016-02-02 18:30:31 +01:00
remitamine
5976e7ab57 [vevo] add support for dash formats 2016-02-02 18:13:01 +01:00
remitamine
a1a22572fb [downloader/dash] make initialization_url optional 2016-02-02 18:12:32 +01:00
remitamine
c11875b328 [facebook] use _parse_mpd 2016-02-02 18:11:16 +01:00
remitamine
8ff648e4f9 [youtube] use _extract_mpd_formats 2016-02-02 18:10:23 +01:00
remitamine
1bac34556f [common] add a generic support for mpd manifests 2016-02-02 18:09:25 +01:00
Sergey M․
0436157b95 [vk:uservideos] Improve _VALID_URL (Closes #8389) 2016-02-02 00:52:37 +06:00
Philipp Hagemeister
ae0db349c1 release 2016.02.01 2016-02-01 12:00:32 +01:00
Yen Chi Hsuan
08411970d5 Merge pull request #8374 from yan12125/facebook-dash
Facebook DASH formats
2016-02-01 18:31:49 +08:00
Yen Chi Hsuan
dc724e0c8b [daum.net:user] Match more URLs (#1952) 2016-02-01 18:26:23 +08:00
Yen Chi Hsuan
0a5d1ec706 Merge branch 'ping-daum-playlist-user' 2016-02-01 18:19:32 +08:00
Yen Chi Hsuan
58250eff2b [daum] Update test_daum_1 2016-02-01 18:19:02 +08:00
Yen Chi Hsuan
11a4efc505 [daum] Do not match a single URL with multiple info extractors 2016-02-01 18:15:53 +08:00
Yen Chi Hsuan
7537b35fb8 [daum] PEP8 2016-02-01 17:40:35 +08:00
Yen Chi Hsuan
33cc74eeeb Merge branch 'daum-playlist-user' of https://github.com/ping/youtube-dl into ping-daum-playlist-user 2016-02-01 17:29:12 +08:00
Yen Chi Hsuan
f021acee49 [kickstarter] Fix title and test_kickstarter
It's the description page that contains a video. The original URL is now
the calendar.
2016-02-01 17:21:40 +08:00
Yen Chi Hsuan
abe694ca95 [kickstarter] Eliminate the warning message and add_ie 2016-02-01 17:10:11 +08:00
Yen Chi Hsuan
b286f201a8 [YoutubeDL] Do not override ie_key in url_transparent 2016-02-01 17:05:48 +08:00
Yen Chi Hsuan
bd93a12e85 [vidzi] Fix _TESTS 2016-02-01 17:03:31 +08:00
Yen Chi Hsuan
92769650fa [vidzi] Fix extraction
Closes #8386.

Vidzi.tv now uses jwplayer, which can be handled by GenericIE
2016-02-01 15:40:42 +08:00
Yen Chi Hsuan
dc4fe5c6d7 [allocine] Use xpath_element 2016-02-01 05:32:28 +08:00
Yen Chi Hsuan
566bda51f2 [bpb] Fix extraction and update tests 2016-02-01 05:00:09 +08:00
Yen Chi Hsuan
f63757ec35 [allocine] Fix for Python 2.6
Python 2.6 does not support .// syntax in find(). Fortunately, the
interested node is at the top level
2016-02-01 03:34:02 +08:00
Yen Chi Hsuan
7a0ed06909 [allocine] Fix extraction of test_allocine_1 and update tests 2016-02-01 03:31:58 +08:00
Yen Chi Hsuan
9934fe76be [acast] Remove ACastBaseIE
No longer necessary as _API_BASE_URL is used by ACastChannelIE only
2016-02-01 03:08:46 +08:00
Yen Chi Hsuan
a8aad21001 [acast] Fix extraction 2016-02-01 03:07:45 +08:00
Yen Chi Hsuan
d055bf91cc Merge branch 'rrooij-gamekings_fix' 2016-02-01 02:21:02 +08:00
Yen Chi Hsuan
0e1b1a011d [gamekings] Stricter checks 2016-02-01 02:19:03 +08:00
Yen Chi Hsuan
eab3c2895c [gamekings] add_ie 2016-02-01 02:15:25 +08:00
Yen Chi Hsuan
163da6a484 [gamekings] Add MD5 back
The test is now a YouTube video, whose MD5 should be stable
2016-02-01 02:13:11 +08:00
Yen Chi Hsuan
324916d11a Merge branch 'gamekings_fix' of https://github.com/rrooij/youtube-dl into rrooij-gamekings_fix 2016-02-01 02:11:25 +08:00
Jaime Marquínez Ferrándiz
3ccb0655c1 [youtube] Use 'orderedSet' instead of 'set' to preserve the order 2016-01-31 15:11:00 +01:00
Jaime Marquínez Ferrándiz
e04398e397 [FFmpegSubtitlesConvertorPP] delete old subtitle files (fixes #8382) 2016-01-31 14:22:36 +01:00
Yen Chi Hsuan
231ea2a3bb [xuite] Replace the test case with my uploaded one 2016-01-31 20:21:57 +08:00
Yen Chi Hsuan
b99d88c6a1 [youporn] Fix uploader and description 2016-01-31 20:12:43 +08:00
Yen Chi Hsuan
189d72d5fd [test_subtitles] Fix TestRaiSubtitles
RaiIE is renamed to RaiTVIE in 06d5556dfa
2016-01-31 20:12:43 +08:00
Yen Chi Hsuan
a7aab0c23e [test_youtube_lists] Fix TestYoutubeLists.test_youtube_course
Youtube entries are now generators
2016-01-31 20:12:43 +08:00
Philipp Hagemeister
a69bee4762 release 2016.01.31 2016-01-31 12:57:18 +01:00
Sergey M․
9acd33094d [youtube] Filter duplicates in playlists base extractor 2016-01-31 17:52:02 +06:00
Sergey M․
8e7aad2075 [youtube] Use authentication for entry list base extractor (Closes #8380) 2016-01-31 17:49:59 +06:00
rrooij
ce5879fa14 [Gamekings] Fix viewing of old videos
Some old videos that aren't on Vimeo are being uploaded to YouTube under the
'Gamekings Vault' channel. They use YouTube now for some videos as video
hosting instead of Vimeo or their own hosting. The first test failed to
succeed under the existing code, but works now by using the YouTube
extractor.

The Regex is changed to find the new gogoVideo JavaScript line with the
YouTube embed. Checking if there is a YouTube embed is done by a String
find, which is probably not the best method of checking this.
2016-01-31 00:20:46 +01:00
Yen Chi Hsuan
7b7507d6e1 [letv] Fix LetvCloud extraction 2016-01-31 07:15:43 +08:00
rrooij
14823decf3 [Gamekings] Fix url from .tv to .nl
Gamekings doesn't use the .tv top level domain anymore, but the regular
domain for Dutch sites.
2016-01-31 00:03:23 +01:00
Sergey M․
673fb82e65 [schooltv] Improve video id regex 2016-01-31 04:41:18 +06:00
Sergey M
181cf24bc0 Merge pull request #8376 from rrooij/schooltv
[schooltv] Add extractor for SchoolTV playlists
2016-01-31 04:36:33 +06:00
rrooij
89f2602880 [schooltv] Add extractor for SchoolTV playlists
This closes #8163
2016-01-30 23:21:42 +01:00
Yen Chi Hsuan
db9b1dbcd9 [nba] Add ext for hls formats and fix test_NBA 2016-01-31 04:58:10 +08:00
Yen Chi Hsuan
e881c4bcab [nbc] Use NBC's id and fix _TESTS
ThePlatform URL gives the same ID for all _TESTS
2016-01-31 04:58:10 +08:00
Yen Chi Hsuan
670ad51ade [nrktv] Fix _TESTS 2016-01-31 04:58:10 +08:00
Yen Chi Hsuan
eb6fc7d32a [senateisvp] Fix test_SenateISVP and test_SenateISVP_1 2016-01-31 04:58:10 +08:00
Yen Chi Hsuan
ed1a390583 [tv2] Fix test_TV2 2016-01-31 04:58:10 +08:00
Yen Chi Hsuan
809e1857c5 [screenwavemedia] Fix HLS extension and test_TeamFour 2016-01-31 04:58:10 +08:00
Yen Chi Hsuan
7c38af48b9 [vgtv] Fix test_VGTV_2 2016-01-31 04:58:10 +08:00
Yen Chi Hsuan
60ad3eb970 [viidea] Skip download for the test case requiring ffmpeg 2016-01-31 04:58:10 +08:00
Sergey M․
a7685b3a6b [npo] Add extension for m3u8 2016-01-31 02:38:28 +06:00
remitamine
8f1fddc816 [limelight] fix format sorting and make m3u8 and f4m extraction non fatal 2016-01-30 20:51:47 +01:00
remitamine
1bf996fa5c [generic] Add support for Limelight API 2016-01-30 20:45:56 +01:00
Yen Chi Hsuan
248ae880b6 [facebook] Add md5 for the test case with DASH 2016-01-30 23:01:19 +08:00
Yen Chi Hsuan
2d2fa82d17 [common] Add _extract_dash_manifest_formats 2016-01-30 22:52:23 +08:00
Yen Chi Hsuan
c94678957f [common] Remove unused arguments 2016-01-30 22:45:16 +08:00
Yen Chi Hsuan
16f38a699f [common] Rename to namespace
For consistency with _parse_smil_*
2016-01-30 22:40:56 +08:00
Yen Chi Hsuan
a6c2c24479 [youtube] Remove '(v|a)codec': 'none' entries
Not used anymore
2016-01-30 22:28:53 +08:00
Sergey M․
b8c9926c0a [downloader/f4m] Do not update fragment list while test 2016-01-30 19:43:25 +06:00
Yen Chi Hsuan
df374b5222 [common] Prefer the manifest than formats_dict in determining codecs 2016-01-30 21:42:27 +08:00
Yen Chi Hsuan
5ea1eb78f5 [common] Fix for youtube 2016-01-30 21:36:01 +08:00
Yen Chi Hsuan
5d2c0fd9ba [youtube] Pass self._formats to _parse_dash_manifest 2016-01-30 21:32:15 +08:00
Yen Chi Hsuan
0803753fea [facebook] Add support for DASH manifests 2016-01-30 21:31:53 +08:00
Sergey M․
2c2f1efdcd [downloader/fragment] Remove superfluous whitespace 2016-01-30 19:30:31 +06:00
Yen Chi Hsuan
b323e1707d [common] Modify _parse_dash_manifest for use in Facebook 2016-01-30 21:27:43 +08:00
Sergey M․
09104e9930 [downloader/f4m] Add live stream flag to context
Now download progress for f4m livestreams is reported correctly
2016-01-30 19:22:15 +06:00
Sergey M․
5fa1702ca6 [downloader/fragment] Do not report total bytes estimation and eta for live streams 2016-01-30 19:20:52 +06:00
Yen Chi Hsuan
17b598d30c [common] _parse_dash_manifest() from youtube.py 2016-01-30 21:05:55 +08:00
Sergey M․
53be8894e4 [options] Add missing closing parenthesis 2016-01-30 18:44:22 +06:00
Sergey M․
c3deacd562 [matchtv] Add extractor (Closes #8313) 2016-01-30 18:30:27 +06:00
Sergey M․
8ab3fe81d8 [downloader/f4m] Prefer bootstrap url attribute over inline bootstrap info 2016-01-30 18:28:38 +06:00
ping
2f0a33d8a3 [daum.net] Support for playlists, user channels 2016-01-30 20:10:36 +08:00
Yen Chi Hsuan
05d0d131a7 [youtube] Move decrypt_sig out of _parse_dash_manifest 2016-01-30 20:05:56 +08:00
Yen Chi Hsuan
c140629995 [facebook] Support alternative webpage form
Fixes #8371
2016-01-30 19:33:22 +08:00
Jaime Marquínez Ferrándiz
7d106a65ca Add --hls-use-mpegts option
When using the mpegts container hls vidoes can be played while being downloaded (useful if you are recording a live stream).
VLC and mpv play them file, but QuickTime doesn't.
2016-01-30 12:26:40 +01:00
Yen Chi Hsuan
0179f6a830 [daum] Add 'thumbnail' to all _TESTS 2016-01-30 16:54:14 +08:00
Yen Chi Hsuan
830afe85dc [daum.net] Support VodPlayer.swf URLs (closes #8173) 2016-01-30 16:50:13 +08:00
Yen Chi Hsuan
8bf39420b4 Merge remote-tracking branch 'upstream/master' 2016-01-30 16:25:55 +08:00
Yen Chi Hsuan
71d08b3e29 Merge branch 'ping-daum-fix-clip' 2016-01-30 16:25:06 +08:00
Yen Chi Hsuan
06ffa33485 [daum.net] Move the request to ClipInfoXml.do
To reduce the number of wasted requests
2016-01-30 16:23:37 +08:00
Yen Chi Hsuan
874e05975b Merge branch 'daum-fix-clip' of https://github.com/ping/youtube-dl into ping-daum-fix-clip 2016-01-30 16:22:37 +08:00
ping
f5d30d521c [daum] Fix add view_count, comment_count to test 2016-01-30 11:09:30 +08:00
ping
e047922be0 [daum] Fix copy-paste mistake 2016-01-30 11:04:11 +08:00
Sergey M․
83ab8a79cc [espn] Improve video id extraction (Closes #8368) 2016-01-30 01:48:54 +06:00
Sergey M․
350cf045d8 [extractor/common] Restrict checks when auto calculating tbr 2016-01-30 01:47:46 +06:00
Sergey M․
68a0ea15b4 [cspan] Unescape path (Closes #8365) 2016-01-30 00:26:33 +06:00
Jaime Marquínez Ferrándiz
2b4f5e68d1 [azubu] Add extractor for live streams (closes #8343) 2016-01-29 15:36:33 +01:00
Philipp Hagemeister
055f417278 release 2016.01.29 2016-01-29 12:20:08 +01:00
Jaime Marquínez Ferrándiz
70029bc348 [youtube:user] Require 'https?://' in the url (fixes #8356)
It was matching www.youtube.com/embed/WpfukLMe1TM.
The generic extractor automatically adds http:// if it's missing.
2016-01-29 11:27:11 +01:00
remitamine
cf57433bbd [ffmpeg] fix adding metadata when using m3u8_native(fixes #8350) 2016-01-28 18:57:32 +01:00
Sergey M․
1ac6e794cb [bbc] Add test for #8147 2016-01-28 23:27:48 +06:00
Sergey M․
a853427427 [bbc] Add another description regex 2016-01-28 23:23:13 +06:00
Sergey M․
50e989e263 [bbc] Add another title regex (Closes #8340) 2016-01-28 23:19:53 +06:00
Sergey M․
10e6ed9341 [ok] Add support for mobile URLs (Closes #8345) 2016-01-28 22:56:49 +06:00
Sergey M․
38c84acae5 [ndr:embed:base] Add missing ext for m3u8 2016-01-28 22:50:18 +06:00
Yen Chi Hsuan
29f46c2bee Credit @dyn888 for improving format selection
[ci skip]
2016-01-28 22:56:59 +08:00
Yen Chi Hsuan
39c10a2b6e Merge pull request #8346 from dyn888/dyn888-regex-1
Regex pattern update to match more codecs (fixes #6858)
2016-01-28 22:22:43 +08:00
dyn888
b913348d5f Test codec with a dot '.' in name selection. 2016-01-28 15:07:33 +01:00
remitamine
2b14cb566f [utils] fix dfxp2srt text extraction(fixes #8055) 2016-01-28 12:38:34 +01:00
dyn888
b0df5223be Update YoutubeDL.py 2016-01-28 12:07:15 +01:00
Sergey M․
ed7cd1e859 [cbsnews] Remove unused import 2016-01-28 00:42:04 +06:00
remitamine
f125d9115b [cbsnews] extract all formats 2016-01-27 19:11:21 +01:00
remitamine
a9d5f12fec Merge pull request #8328 from remitamine/hls-master-detect
[extractor/common] detect media playlist in _extract_m3u8_formats
2016-01-27 18:07:30 +01:00
remitamine
7f32e5dc35 [extractor/common] detect media playlist in _extract_m3u8_formats 2016-01-27 17:53:42 +01:00
Sergey M․
c3111ab34f [spankbang] Fix title extraction (Closes #8329) 2016-01-27 21:49:56 +06:00
Sergey M․
9339774af2 [spankbang] Fix formats extraction 2016-01-27 21:49:39 +06:00
Sergey M․
b0d21deda9 [extractor/common] Auto calculate tbr when missing 2016-01-27 21:11:17 +06:00
Philipp Hagemeister
fab6f0e65b release 2016.01.27 2016-01-27 08:32:03 +01:00
ping
b6c33fd544 [daum.net] Fixes #8331 2016-01-27 12:48:00 +08:00
Sergey M․
fb4b345800 [instagram] Make description optional (Closes #8326) 2016-01-26 21:46:51 +06:00
Sergey M․
af9c2a07ae [cspan] Extract from path when no qualities (Closes #8317) 2016-01-26 21:29:42 +06:00
remitamine
ab180fc648 Merge branch 'master' of github.com:rg3/youtube-dl 2016-01-26 15:55:38 +01:00
remitamine
682f8c43b5 [vevo] fallback to youtube video only if vevo video is geo restricted(fixes 8263)(fixes 2874) 2016-01-26 15:54:32 +01:00
Sergey M․
f693213567 [cspan] Fix clip/prog id extraction (#8317) 2016-01-26 20:42:20 +06:00
remitamine
9165d6bab9 [vevo] extract metadata and formats from api if videoinfo is empty
these was fixed by @yan12125 in ff51983e15
i only added some code to extract video metadata and more formats from
api
2016-01-26 13:46:58 +01:00
remitamine
2975fe1a7b [vevo] extract all formats and bypass geo restriction 2016-01-25 22:35:06 +01:00
Sergey M․
de691a498d [facebook:post] Add extractor (Closes #8321) 2016-01-25 22:18:34 +06:00
Sergey M․
2e6e742c3c [facebook] Add shortcut and reformat _VALID_URL 2016-01-25 22:15:21 +06:00
Yen Chi Hsuan
e9bd0f772b Merge pull request #8130 from dyn888/master
[youtube] added vcodec/acodec/abr for multiple itags
2016-01-25 01:15:11 +08:00
Yen Chi Hsuan
77f785076f [common] Keep full codec name from m3u8 manifests
See #8293. This is for consistency between YouTube and HLS formats.
2016-01-25 01:03:46 +08:00
Yen Chi Hsuan
94278f7202 [youtube] Prefer info from YouTube than _formats (#8293) 2016-01-25 01:02:19 +08:00
Yen Chi Hsuan
a0d8d704df [utils] Reorder items in mimetype2ext alphabetically 2016-01-25 01:01:15 +08:00
Yen Chi Hsuan
f6861ec96f [utils] Add more items to mimetype2ext (#8293)
These are used in Youtube formats
2016-01-25 00:58:53 +08:00
Philipp Hagemeister
f733b05302 release 2016.01.23 2016-01-23 12:03:12 +01:00
Sergey M․
6fa73386cb [drtv] Use IETF language tag 2016-01-23 01:54:00 +06:00
Sergey M․
5ca01bb9e4 [kanalplay] Use IETF language tag 2016-01-23 01:51:18 +06:00
Sergey M․
1ca59daca9 [options] Clarify language tags 2016-01-23 01:50:06 +06:00
Sergey M․
594c4d79a5 [svt] Improve subtitles extraction and add test (Closes #8265) 2016-01-23 01:47:54 +06:00
Marian Sigler
1f16b958b1 [SVTPlay] Add subtitle support 2016-01-23 01:28:31 +06:00
Sergey M․
4c0d13df9b [lovehomeporn] Add extractor 2016-01-23 00:52:23 +06:00
Sergey M․
b2c6528baf [ruleporn] Rework in terms of nuevo (Closes #8206) 2016-01-23 00:40:11 +06:00
Sergey M․
ea17820432 [nuevo] Improve thumbnail extraction 2016-01-23 00:38:58 +06:00
Dankryn
1257b049bc [ruleporn] Add new extractor 2016-01-23 00:13:27 +06:00
Sergey M․
b969813548 Credit @nexAkari for trollvids and nuevo (#7728) 2016-01-23 00:10:49 +06:00
Sergey M․
10677ece81 [nuevo] Simplify nuevo extractors (Closes #7728) 2016-01-23 00:04:33 +06:00
Andrew "Akari" Alexeyew
d570746e45 [nuevo] Generalize nuevo extractor and add support for trollvids
Supports only the nuevo player for now (most common).

[trollvids] convert duration to an int

[trollvids] added a test

[trollvids] made flake8 shut up

Generalized the Nuevo extractor

Affects: anitube, trollvids, trutube

[nuevo] Complied with the code comments.
2016-01-22 23:29:24 +06:00
Sergey M․
4fcd9d147d [arte:cinema] Add extractor 2016-01-22 23:00:50 +06:00
Sergey M․
9c54ae3387 [arte:future] Make duplicated test matching only 2016-01-22 23:00:05 +06:00
François Charlier
24114fee74 [arte:future] Fix extraction
[arte] Add support for more "Arte Future" uri
2016-01-22 22:58:37 +06:00
Sergey M․
220ee33f2b [cbsnews] Simplify subtitles extraction and fix test (Closes #8295) 2016-01-22 22:23:21 +06:00
John Assael
4118cc02c1 [cbsnews] Extract subtitles
added test function for CBS News subtitles
2016-01-22 22:15:51 +06:00
Jaime Marquínez Ferrándiz
32d77eeb04 [downloader/common] report_retry: Don't crash when retries is infinite (fixes #8299) 2016-01-22 14:49:17 +01:00
Filippo Valsorda
032f232626 Merge pull request #8142 from FiloSottile/filippo/updates
[update] fix (unexploitable) BB'06 vulnerability in rsa_verify
2016-01-21 20:17:37 +00:00
Filippo Valsorda
4d318be195 [update] fix (unexploitable) BB'06 vulnerability in rsa_verify
The rsa_verify code was vulnerable to a BB'06 attack, allowing to forge
signatures for arbitrary messages if and only if the public key exponent is
3.  Since the updates key is hardcoded to 65537, there is no risk for
youtube-dl, but I don't want vulnerable code in the wild.

The new function adopts a way safer approach of encoding-and-comparing to
replace the dangerous parsing code.
2016-01-21 20:12:17 +00:00
Yen Chi Hsuan
6b45f9aba2 [iqiyi] Update key (closes #8292) 2016-01-22 02:14:47 +08:00
Sergey M․
1e10d02fec [hitbox] Skip subscribe only formats (Closes #8217) 2016-01-21 23:28:22 +06:00
Sergey M․
51290d8457 [youtube] Simplify automatic captions URL check (Closes #8287) 2016-01-21 22:58:03 +06:00
Dimitre Liotev
582f4f834e Fix issue #8109 (error when downloading automatic captions) 2016-01-21 22:55:36 +06:00
Sergey M․
e87d98b0dd [yahoo] Add improve content id regexes (Closes #8290) 2016-01-21 22:42:50 +06:00
igv
383496e65e Additional regex for yahoo extractor 2016-01-21 22:35:28 +06:00
Jaime Marquínez Ferrándiz
4519c1f43c [vimeo] 'ext' must be a string, not a tuple (fixes #8288)
There was an ',' at the end of the line.
2016-01-21 12:43:45 +01:00
Sergey M․
a616f65471 [tube8] PEP 8 2016-01-20 21:30:29 +06:00
CeruleanSky
1f78ed189a [OraTV] update extractor
"current" is now "video"
"hls_stream" is now hls_stream without quotes
video_id is now id
duration for current video is not present(for other videos it is)

modified regex to find hls_stream variable to work reguardless of whether it is quoted or not.

[ora] Improve (Closes #8273)
2016-01-20 21:28:42 +06:00
Sergey M․
7dde358adc [tube8] Extract duration and modernize 2016-01-20 20:07:32 +06:00
Sergey M․
27b83249c9 [tube8] Fix extraction and extract all formats (Closes #8281) 2016-01-20 20:00:51 +06:00
Yen Chi Hsuan
56aa074538 Credit @FounderSG for WeiqiTV and LetvCloud (#7994)
[ci skip]
2016-01-20 13:20:03 +08:00
Jaime Marquínez Ferrándiz
9d90e7de03 [downloader/hls] Ask ffmpeg to quit when interrupting youtube-dl with 'Ctrl+C' (#8252)
Otherwise the mp4 file can't be played.
2016-01-19 22:07:14 +01:00
Yen Chi Hsuan
7d4d9c526a Merge branch 'ping-patch-8239' 2016-01-20 04:22:25 +08:00
Yen Chi Hsuan
fe6856b059 [neteasemusic] Use float_or_none 2016-01-20 04:21:51 +08:00
Yen Chi Hsuan
a54fbf2ca6 Merge branch 'patch-8239' of https://github.com/ping/youtube-dl into ping-patch-8239 2016-01-20 04:15:46 +08:00
Yen Chi Hsuan
d8024aebe5 Merge branch 'FounderSG-Weiqitv' 2016-01-20 04:06:09 +08:00
Yen Chi Hsuan
8652bd22f1 [weiqitv] Use single quotes 2016-01-20 04:04:39 +08:00
Yen Chi Hsuan
f15a9ca301 [weiqitv] Rename the extractor - capitilize 'TV' 2016-01-20 04:03:57 +08:00
Yen Chi Hsuan
65ced034b8 [weiqitv] Make codes shorter 2016-01-20 04:02:30 +08:00
Yen Chi Hsuan
bec30224ff [letv] LetvCloud: Detect ext instead of the hardcoded one 2016-01-20 04:00:37 +08:00
Yen Chi Hsuan
0428106da3 [letv] LetvCloud: make title looks like a title 2016-01-20 03:53:17 +08:00
Yen Chi Hsuan
73e7442456 [letv] LetvCloud: simplify and improve _VALID_URL 2016-01-20 03:42:01 +08:00
Yen Chi Hsuan
26de1bba83 [letv] LetvCloud: check error messages from server 2016-01-20 03:31:34 +08:00
Yen Chi Hsuan
e0690782b8 [letv] LetvCloud: guard against invalid URLs 2016-01-20 03:25:12 +08:00
Yen Chi Hsuan
8fff4f61e5 [letv] Use single quotes 2016-01-20 03:18:54 +08:00
Yen Chi Hsuan
10defdd06a [letv] Reduce duplicated codes 2016-01-20 03:17:35 +08:00
Sergey M․
485139c15c [viewster] Tolerate missing synopsis (Closes #8274) 2016-01-20 00:02:46 +06:00
Sergey M․
b605ebb609 [lemonde] Add extractor 2016-01-19 22:09:55 +06:00
Sergey M․
aecfcd4e59 [ultimedia] Rename to digiteka 2016-01-19 21:51:46 +06:00
Sergey M․
942d46196f [ultimedia] Extend _VALID_URL to support digiteka 2016-01-19 21:47:06 +06:00
Yen Chi Hsuan
78be2eca7c Merge branch 'Weiqitv' of https://github.com/FounderSG/youtube-dl into FounderSG-Weiqitv 2016-01-19 23:39:32 +08:00
Sergey M․
1fa2b9841d [extractor/generic] Extend dailymotion embed regex 2016-01-19 21:20:45 +06:00
Sergey M․
9fbd0822aa [dailymotion] Extend _VALID_URL 2016-01-19 21:20:14 +06:00
Sergey M․
e323cf3ff3 [youtube] Skip test 2016-01-19 20:56:04 +06:00
Sergey M․
8ceabd4df3 [youtube] Capture and output unavailable message 2016-01-19 20:54:43 +06:00
Sergey M․
a8776b107b [youtube] Clarify test_Youtube_18 2016-01-18 23:19:38 +06:00
Sergey M․
096b533982 [youtube] Fix URL expansion in video description
Fixes test_Youtube_18
2016-01-18 23:17:45 +06:00
Sergey M․
dae503afaa [atresplayer] Skip HLS completely (Closes #8261) 2016-01-17 22:14:07 +06:00
Yen Chi Hsuan
b39eab7f94 Merge pull request #8262 from jwilk/https-everywhere
[ustream] Use HTTPS for GitHub URL
2016-01-17 22:10:03 +08:00
Jakub Wilk
e5a66240c0 [ustream] Use HTTPS for GitHub URL 2016-01-17 15:06:00 +01:00
ping
e0ef13ddeb [neteasemusic] Fallback to alt hosts if m5.music.126.net doesn't work 2016-01-17 07:48:46 +08:00
Sergey M․
855f90fa6f [ae] Rename to aenetworks and clarify extractor name and description 2016-01-17 03:02:45 +06:00
Yen Chi Hsuan
614db89ae3 [compat] Clarify the versions requiring compat_kwargs
It's supported since 2.7.0 alpha 1 and 2.6.5 rc 1. See
https://hg.python.org/cpython/file/v2.7a1/Misc/NEWS#l337
https://hg.python.org/cpython/file/v2.6.5rc1/Misc/NEWS#l28
2016-01-16 22:17:31 +08:00
Yen Chi Hsuan
1358b94163 [ae] Fix _TESTS 2016-01-16 20:56:53 +08:00
Yen Chi Hsuan
350e02d40d [bbc] Use _search_json_ld 2016-01-16 20:46:28 +08:00
Yen Chi Hsuan
0b26ba3fc8 [extractor/common] Allow passing more parameters to _search_json_ld 2016-01-16 20:45:36 +08:00
ping
3a0a78731b Fixes #8239 2016-01-16 12:17:07 +08:00
Sergey M
6be16ed24b [README.md] Add protocol usage example in format selection 2016-01-16 10:15:24 +06:00
Sergey M․
b555942428 [YoutubeDL] Ensure protocol is always present 2016-01-16 10:10:28 +06:00
Sergey M
b2dca40d81 [README.md] Improve format selection documentation 2016-01-16 09:55:52 +06:00
Sergey M
15870bbd01 [README.md] Mention new string operators for format selection 2016-01-16 09:53:31 +06:00
Yen Chi Hsuan
10d33b3473 [YoutubeDL] Introduce CSS3 like string operators 2016-01-16 09:53:12 +06:00
Sergey M
ac25992bc7 Merge pull request #8246 from dstftw/initial-json-ld-metadata-support
Initial JSON-LD metadata extraction support
2016-01-16 07:20:15 +06:00
Sergey M
30783c442d Merge pull request #8245 from dstftw/auto-generate-title-fields
[YoutubeDL] Auto generate title fields corresponding to the *_number fields
2016-01-16 07:20:03 +06:00
Sergey M․
a50a8003a0 [cultureunplugged] Improve (Closes #8060) 2016-01-16 07:10:51 +06:00
Sergey M․
315bdae00a [zippcast] Improve (Closes #8198) 2016-01-16 06:27:34 +06:00
ckuu
2ddfd26f1b '[ZippCast] Add new extractor'
Closes rg3/youtube-dl#6591
2016-01-16 06:25:06 +06:00
Sergey M․
b4e44234bc [ae] Use JSON-LD for TV series metadata 2016-01-16 00:36:49 +06:00
Sergey M․
4ca2a3cf3c [extractor/common] Add initial support for JSON-LD metadata extraction into info_dict 2016-01-16 00:36:02 +06:00
Sergey M․
33d2fc2f64 [YoutubeDL] Auto generate title fields corresponding to the *_number fields
Auto generate title fields corresponding to the *_number fields when missing in order to always have clean titles. This is very common for TV series.
2016-01-16 00:09:54 +06:00
dyn888
e1a0bfdffe [youtube] added vcodec/acodec/abr for multiple itags
Should make downloading with filters more precise and easier, ie. bestvideo[vcodec=h264]. By default a lot of codecs are specified as avc1.xxxxxx and unique for each format, which makes them unusable for bestvideo selection.
2016-01-03 04:11:19 +01:00
Founder Fang
5f432ac8f5 [Weiqitv] Add new extractor 2015-12-22 06:21:56 +08:00
223 changed files with 6795 additions and 2259 deletions

3
.gitignore vendored
View File

@@ -1,5 +1,6 @@
*.pyc
*.pyo
*.class
*~
*.DS_Store
wine-py2exe/
@@ -32,4 +33,4 @@ test/testdata
.tox
youtube-dl.zsh
.idea
.idea/*
.idea/*

View File

@@ -153,3 +153,11 @@ flatgreen
Brian Foley
Vignesh Venkat
Tom Gijselinck
Founder Fang
Andrew Alexeyew
Saso Bezlaj
Erwin de Haan
Jens Wille
Robin Houtevelts
Patrick Griffis
Aidan Rowe

View File

@@ -1,6 +1,6 @@
**Please include the full output of youtube-dl when run with `-v`**, i.e. add `-v` flag to your command line, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
**Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
```
$ youtube-dl -v http://www.youtube.com/watch?v=BaW_jenozKcj
$ youtube-dl -v <your command line>
[debug] System config: []
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
@@ -92,7 +92,9 @@ If you want to create a build of youtube-dl yourself, you'll need
### Adding support for a new site
If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
@@ -140,16 +142,17 @@ If you want to add support for a new site, you can follow this quick list (assum
```
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want.
8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
9. Check the code with [flake8](https://pypi.python.org/pypi/flake8).
10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/__init__.py
$ git add youtube_dl/extractor/yourextractor.py
$ git commit -m '[yourextractor] Add new extractor'
$ git push origin yourextractor
10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
In any case, thank you very much for your contributions!

View File

@@ -3,6 +3,7 @@ all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bas
clean:
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
find . -name "*.pyc" -delete
find . -name "*.class" -delete
PREFIX ?= /usr/local
BINDIR ?= $(PREFIX)/bin
@@ -44,7 +45,7 @@ test:
ot: offlinetest
offlinetest: codetest
nosetests --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py
$(PYTHON) -m nose --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py
tar: youtube-dl.tar.gz

222
README.md
View File

@@ -80,6 +80,8 @@ which means you can modify it, redistribute it or use it however you like.
on Windows)
--flat-playlist Do not extract the videos of a playlist,
only list them.
--mark-watched Mark videos watched (YouTube only)
--no-mark-watched Do not mark videos watched (YouTube only)
--no-color Do not emit color codes in output
## Network Options:
@@ -173,6 +175,10 @@ which means you can modify it, redistribute it or use it however you like.
expected filesize (experimental)
--hls-prefer-native Use the native HLS downloader instead of
ffmpeg (experimental)
--hls-use-mpegts Use the mpegts container for HLS videos,
allowing to play the video while
downloading (some players may not be able
to play it)
--external-downloader COMMAND Use the specified external downloader.
Currently supports
aria2c,axel,curl,httpie,wget
@@ -339,8 +345,8 @@ which means you can modify it, redistribute it or use it however you like.
preference, for example: "srt" or
"ass/srt/best"
--sub-lang LANGS Languages of the subtitles to download
(optional) separated by commas, use IETF
language tags like 'en,pt'
(optional) separated by commas, use --list-
subs for available language tags
## Authentication Options:
-u, --username USERNAME Login with this account ID
@@ -405,13 +411,18 @@ which means you can modify it, redistribute it or use it however you like.
# CONFIGURATION
You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime and use a proxy:
You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`.
For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory:
```
--extract-audio
-x
--no-mtime
--proxy 127.0.0.1:3128
-o ~/Movies/%(title)s.%(ext)s
```
Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`.
You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run.
### Authentication with `.netrc` file
@@ -436,43 +447,189 @@ On Windows you may also need to setup the `%HOME%` environment variable manually
# OUTPUT TEMPLATE
The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are:
The `-o` option allows users to indicate a template for the output file names.
- `id`: The sequence will be replaced by the video identifier.
- `url`: The sequence will be replaced by the video URL.
- `uploader`: The sequence will be replaced by the nickname of the person who uploaded the video.
- `upload_date`: The sequence will be replaced by the upload date in YYYYMMDD format.
- `title`: The sequence will be replaced by the video title.
- `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4).
- `epoch`: The sequence will be replaced by the Unix epoch when creating the file.
- `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
- `playlist`: The sequence will be replaced by the name or the id of the playlist that contains the video.
- `playlist_index`: The sequence will be replaced by the index of the video in the playlist padded with leading zeros according to the total length of the playlist.
- `format_id`: The sequence will be replaced by the format code specified by `--format`.
- `duration`: The sequence will be replaced by the length of the video in seconds.
**tl;dr:** [navigate me to examples](#output-template-examples).
The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are:
- `id`: Video identifier
- `title`: Video title
- `url`: Video URL
- `ext`: Video filename extension
- `alt_title`: A secondary title of the video
- `display_id`: An alternative identifier for the video
- `uploader`: Full name of the video uploader
- `license`: License name the video is licensed under
- `creator`: The main artist who created the video
- `release_date`: The date (YYYYMMDD) when the video was released
- `timestamp`: UNIX timestamp of the moment the video became available
- `upload_date`: Video upload date (YYYYMMDD)
- `uploader_id`: Nickname or id of the video uploader
- `location`: Physical location where the video was filmed
- `duration`: Length of the video in seconds
- `view_count`: How many users have watched the video on the platform
- `like_count`: Number of positive ratings of the video
- `dislike_count`: Number of negative ratings of the video
- `repost_count`: Number of reposts of the video
- `average_rating`: Average rating give by users, the scale used depends on the webpage
- `comment_count`: Number of comments on the video
- `age_limit`: Age restriction for the video (years)
- `format`: A human-readable description of the format
- `format_id`: Format code specified by `--format`
- `format_note`: Additional info about the format
- `width`: Width of the video
- `height`: Height of the video
- `resolution`: Textual description of width and height
- `tbr`: Average bitrate of audio and video in KBit/s
- `abr`: Average audio bitrate in KBit/s
- `acodec`: Name of the audio codec in use
- `asr`: Audio sampling rate in Hertz
- `vbr`: Average video bitrate in KBit/s
- `fps`: Frame rate
- `vcodec`: Name of the video codec in use
- `container`: Name of the container format
- `filesize`: The number of bytes, if known in advance
- `filesize_approx`: An estimate for the number of bytes
- `protocol`: The protocol that will be used for the actual download
- `extractor`: Name of the extractor
- `extractor_key`: Key name of the extractor
- `epoch`: Unix epoch when creating the file
- `autonumber`: Five-digit number that will be increased with each download, starting at zero
- `playlist`: Name or id of the playlist that contains the video
- `playlist_index`: Index of the video in the playlist padded with leading zeros according to the total length of the playlist
Available for the video that belongs to some logical chapter or section:
- `chapter`: Name or title of the chapter the video belongs to
- `chapter_number`: Number of the chapter the video belongs to
- `chapter_id`: Id of the chapter the video belongs to
Available for the video that is an episode of some series or programme:
- `series`: Title of the series or programme the video episode belongs to
- `season`: Title of the season the video episode belongs to
- `season_number`: Number of the season the video episode belongs to
- `season_id`: Id of the season the video episode belongs to
- `episode`: Title of the video episode
- `episode_number`: Number of the video episode within a season
- `episode_id`: Id of the video episode
Each aforementioned sequence when referenced in output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by particular extractor, such sequences will be replaced with `NA`.
For example for `-o %(title)s-%(id)s.%(ext)s` and mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj` this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory.
Output template can also contain arbitrary hierarchical path, e.g. `-o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s'` that will result in downloading each video in a directory corresponding to this path template. Any missing directory will be automatically created for you.
To specify percent literal in output template use `%%`. To output to stdout use `-o -`.
The current default template is `%(title)s-%(id)s.%(ext)s`.
In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:
#### Output template examples
Note on Windows you may need to use double quotes instead of single.
```bash
$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc
$ youtube-dl --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc
youtube-dl test video ''_ä↭𝕐.mp4 # All kinds of weird characters
$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
$ youtube-dl --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc --restrict-filenames
youtube-dl_test_video_.mp4 # A simple file name
# Download YouTube playlist videos in separate directory indexed by video order in a playlist
$ youtube-dl -o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
# Download all playlists of YouTube channel/user keeping each playlist in separate directory:
$ youtube-dl -o '%(uploader)s/%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/user/TheLinuxFoundation/playlists
# Download Udemy course keeping each chapter in separate directory under MyVideos directory in your home
$ youtube-dl -u user -p password -o '~/MyVideos/%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/
# Download entire series season keeping each series and each season in separate directory under C:/MyVideos
$ youtube-dl -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" http://videomore.ru/kino_v_detalayah/5_sezon/367617
# Stream the video being downloaded to stdout
$ youtube-dl -o - BaW_jenozKc
```
# FORMAT SELECTION
By default youtube-dl tries to download the best quality, but sometimes you may want to download in a different format.
The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`.
By default youtube-dl tries to download the best available quality, i.e. if you want the best quality you **don't need** to pass any special options, youtube-dl will guess it for you by **default**.
If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`). This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`. Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`.
But sometimes you may want to download in a different format, for example when you are on a slow or intermittent connection. The key mechanism for achieving this is so called *format selection* based on which you can explicitly specify desired format, select formats based on some criterion or criteria, setup precedence and much more.
Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
The general syntax for format selection is `--format FORMAT` or shorter `-f FORMAT` where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download.
**tl;dr:** [navigate me to examples](#format-selection-examples).
The simplest case is requesting a specific format, for example with `-f 22` you can download the format with format code equal to 22. You can get the list of available format codes for particular video using `--list-formats` or `-F`. Note that these format codes are extractor specific.
You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download best quality format of particular file extension served as a single file, e.g. `-f webm` will download best quality format with `webm` extension served as a single file.
You can also use special names to select particular edge case format:
- `best`: Select best quality format represented by single file with video and audio
- `worst`: Select worst quality format represented by single file with video and audio
- `bestvideo`: Select best quality video only format (e.g. DASH video), may not be available
- `worstvideo`: Select worst quality video only format, may not be available
- `bestaudio`: Select best quality audio only format, may not be available
- `worstaudio`: Select worst quality audio only format, may not be available
For example, to download worst quality video only format you can use `-f worstvideo`.
If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes. Note that slash is left-associative, i.e. formats on the left hand side are preferred, for example `-f 22/17/18` will download format 22 if it's available, otherwise it will download format 17 if it's available, otherwise it will download format 18 if it's available, otherwise it will complain that no suitable formats are available for download.
If you want to download several formats of the same video use comma as a separator, e.g. `-f 22,17,18` will download all these three formats, of course if they are available. Or more sophisticated example combined with precedence feature `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`.
You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`).
The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals):
- `filesize`: The number of bytes, if known in advance
- `width`: Width of the video, if known
- `height`: Height of the video, if known
- `tbr`: Average bitrate of audio and video in KBit/s
- `abr`: Average audio bitrate in KBit/s
- `vbr`: Average video bitrate in KBit/s
- `asr`: Audio sampling rate in Hertz
- `fps`: Frame rate
Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begins with), `$=` (ends with), `*=` (contains) and following string meta fields:
- `ext`: File extension
- `acodec`: Name of the audio codec in use
- `vcodec`: Name of the video codec in use
- `container`: Name of the container format
- `protocol`: The protocol that will be used for the actual download, lower-case. `http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `m3u8`, or `m3u8_native`
Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by video hoster.
Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s.
You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv installed), for example `-f bestvideo+bestaudio` will download best video only format, best audio only format and mux them together with ffmpeg/avconv.
Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`.
Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see [#5447](https://github.com/rg3/youtube-dl/issues/5447), [#5456](https://github.com/rg3/youtube-dl/issues/5456)). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download the best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
#### Format selection examples
Note on Windows you may need to use double quotes instead of single.
```bash
# Download best mp4 format available or any other best if no mp4 available
$ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best'
# Download best format available but not better that 480p
$ youtube-dl -f 'bestvideo[height<=480]+bestaudio/best[height<=480]'
# Download best video only format but no bigger that 50 MB
$ youtube-dl -f 'best[filesize<50M]'
# Download best format available via direct link over HTTP/HTTPS protocol
$ youtube-dl -f '(bestvideo+bestaudio/best)[protocol^=http]'
```
# VIDEO SELECTION
Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`. They accept dates in two formats:
@@ -598,7 +755,7 @@ means you're using an outdated version of Python. Please update to Python 2.6 or
### What is this binary file? Where has the code gone?
Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.
Since June 2012 ([#342](https://github.com/rg3/youtube-dl/issues/342)) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.
### The exe throws a *Runtime error from Visual C++*
@@ -681,7 +838,9 @@ If you want to create a build of youtube-dl yourself, you'll need
### Adding support for a new site
If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
@@ -729,16 +888,17 @@ If you want to add support for a new site, you can follow this quick list (assum
```
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want.
8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
9. Check the code with [flake8](https://pypi.python.org/pypi/flake8).
10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/__init__.py
$ git add youtube_dl/extractor/yourextractor.py
$ git commit -m '[yourextractor] Add new extractor'
$ git push origin yourextractor
10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
In any case, thank you very much for your contributions!
@@ -800,9 +960,9 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>. Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the IRC channel [#youtube-dl](irc://chat.freenode.net/#youtube-dl) on freenode ([webchat](http://webchat.freenode.net/?randomnick=1&channels=youtube-dl)).
**Please include the full output of youtube-dl when run with `-v`**, i.e. add `-v` flag to your command line, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
**Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this:
```
$ youtube-dl -v http://www.youtube.com/watch?v=BaW_jenozKcj
$ youtube-dl -v <your command line>
[debug] System config: []
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']

View File

@@ -24,12 +24,13 @@
- **AdobeTVShow**
- **AdobeTVVideo**
- **AdultSwim**
- **AE**
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
- **Aftonbladet**
- **AirMozilla**
- **AlJazeera**
- **Allocine**
- **AlphaPorno**
- **AnimeOnDemand**
- **anitube.se**
- **AnySex**
- **Aparat**
@@ -43,17 +44,20 @@
- **ARD:mediathek**
- **arte.tv**
- **arte.tv:+7**
- **arte.tv:cinema**
- **arte.tv:concert**
- **arte.tv:creative**
- **arte.tv:ddc**
- **arte.tv:embed**
- **arte.tv:future**
- **arte.tv:magazine**
- **AtresPlayer**
- **ATTTechChannel**
- **AudiMedia**
- **audiomack**
- **audiomack:album**
- **Azubu**
- **AzubuLive**
- **BaiduVideo**: 百度视频
- **bambuser**
- **bambuser:channel**
@@ -73,6 +77,7 @@
- **BleacherReportCMS**
- **blinkx**
- **Bloomberg**
- **BokeCC**
- **Bpb**: Bundeszentrale für politische Bildung
- **BR**: Bayerischer Rundfunk Mediathek
- **Break**
@@ -87,8 +92,11 @@
- **canalc2.tv**
- **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
- **Canvas**
- **CBC**
- **CBCPlayer**
- **CBS**
- **CBSNews**: CBS News
- **CBSNewsLiveVideo**: CBS News Live Videos
- **CBSSports**
- **CeskaTelevize**
- **channel9**: Channel 9
@@ -117,6 +125,7 @@
- **ComedyCentralShows**: The Daily Show / The Colbert Report
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
- **Cracked**
- **Crackle**
- **Criterion**
- **CrooksAndLiars**
- **Crunchyroll**
@@ -124,6 +133,7 @@
- **CSpan**: C-SPAN
- **CtsNews**: 華視新聞
- **culturebox.francetvinfo.fr**
- **CultureUnplugged**
- **CWTV**
- **dailymotion**
- **dailymotion:playlist**
@@ -131,6 +141,8 @@
- **DailymotionCloud**
- **daum.net**
- **daum.net:clip**
- **daum.net:playlist**
- **daum.net:user**
- **DBTV**
- **DCN**
- **dcn:live**
@@ -141,6 +153,7 @@
- **defense.gouv.fr**
- **democracynow**
- **DHM**: Filmarchiv - Deutsches Historisches Museum
- **Digiteka**
- **Discovery**
- **Dotsub**
- **DouyuTV**: 斗鱼
@@ -177,9 +190,11 @@
- **ExpoTV**
- **ExtremeTube**
- **facebook**
- **facebook:post**
- **faz.net**
- **fc2**
- **Fczenit**
- **features.aol.com**
- **fernsehkritik.tv**
- **Firstpost**
- **FiveTV**
@@ -254,7 +269,7 @@
- **Instagram**
- **instagram:user**: Instagram user profile
- **InternetVideoArchive**
- **IPrima** (Currently broken)
- **IPrima**
- **iqiyi**: 爱奇艺
- **Ir90Tv**
- **ivi**: ivi.ru
@@ -275,9 +290,11 @@
- **KeezMovies**
- **KhanAcademy**
- **KickStarter**
- **KonserthusetPlay**
- **kontrtube**: KontrTube.ru - Труба зовёт
- **KrasView**: Красвью
- **Ku6**
- **KUSI**
- **kuwo:album**: 酷我音乐 - 专辑
- **kuwo:category**: 酷我音乐 - 分类
- **kuwo:chart**: 酷我音乐 - 排行榜
@@ -286,10 +303,11 @@
- **kuwo:song**: 酷我音乐
- **la7.tv**
- **Laola1Tv**
- **Le**: 乐视网
- **Lecture2Go**
- **Letv**: 乐视网
- **LetvPlaylist**
- **LetvTv**
- **Lemonde**
- **LePlaylist**
- **LetvCloud**: 乐视云
- **Libsyn**
- **life:embed**
- **lifenews**: LIFE | NEWS
@@ -300,6 +318,7 @@
- **livestream**
- **livestream:original**
- **LnkGo**
- **LoveHomePorn**
- **lrt.lt**
- **lynda**: lynda.com videos
- **lynda:course**: lynda.com online courses
@@ -308,6 +327,7 @@
- **mailru**: Видео@Mail.Ru
- **MakerTV**
- **Malemotion**
- **MatchTV**
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
- **metacafe**
@@ -344,7 +364,7 @@
- **MySpace:album**
- **MySpass**
- **Myvi**
- **myvideo**
- **myvideo** (Currently broken)
- **MyVidster**
- **n-tv.de**
- **NationalGeographic**
@@ -394,6 +414,7 @@
- **NowTV** (Currently broken)
- **NowTVList**
- **nowvideo**: NowVideo
- **Noz**
- **npo**: npo.nl and ntr.nl
- **npo.nl:live**
- **npo.nl:radio**
@@ -401,6 +422,7 @@
- **Npr**
- **NRK**
- **NRKPlaylist**
- **NRKSkole**: NRK Skole
- **NRKTV**: NRK TV and NRK Radio
- **ntv.ru**
- **Nuvid**
@@ -432,6 +454,7 @@
- **PlanetaPlay**
- **play.fm**
- **played.to**
- **PlaysTV**
- **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
- **Playvid**
- **Playwire**
@@ -443,6 +466,7 @@
- **PornHd**
- **PornHub**
- **PornHubPlaylist**
- **PornHubUserVideos**
- **Pornotube**
- **PornoVoisines**
- **PornoXO**
@@ -486,6 +510,7 @@
- **rtve.es:live**: RTVE.es live streams
- **RTVNH**
- **RUHD**
- **RulePorn**
- **rutube**: Rutube videos
- **rutube:channel**: Rutube channels
- **rutube:embed**: Rutube embedded videos
@@ -499,10 +524,12 @@
- **Sapo**: SAPO Vídeos
- **savefrom.net**
- **SBS**: sbs.com.au
- **schooltv**
- **SciVee**
- **screen.yahoo:search**: Yahoo screen search
- **Screencast**
- **ScreencastOMatic**
- **ScreenJunkies**
- **ScreenwaveMedia**
- **SenateISVP**
- **ServingSys**
@@ -536,7 +563,6 @@
- **southpark.de**
- **southpark.nl**
- **southparkstudios.dk**
- **Space**
- **SpankBang**
- **Spankwire**
- **Spiegel**
@@ -596,12 +622,14 @@
- **TMZ**
- **TMZArticle**
- **TNAFlix**
- **TNAFlixNetworkEmbed**
- **toggle**
- **tou.tv**
- **Toypics**: Toypics user profile
- **ToypicsUser**: Toypics user profile
- **TrailerAddict** (Currently broken)
- **Trilulilu**
- **trollvids**
- **TruTube**
- **Tube8**
- **TubiTv**
@@ -635,16 +663,17 @@
- **twitch:video**
- **twitch:vod**
- **twitter**
- **twitter:amplify**
- **twitter:card**
- **Ubu**
- **udemy**
- **udemy:course**
- **UDNEmbed**: 聯合影音
- **Ultimedia**
- **Unistra**
- **Urort**: NRK P3 Urørt
- **ustream**
- **ustream:channel**
- **Ustudio**
- **Varzesh3**
- **Vbox7**
- **VeeHD**
@@ -660,14 +689,16 @@
- **video.mit.edu**
- **VideoDetective**
- **videofy.me**
- **VideoMega** (Currently broken)
- **VideoMega**
- **videomore**
- **videomore:season**
- **videomore:video**
- **VideoPremium**
- **VideoTt**: video.tt - Your True Tube (Currently broken)
- **videoweed**: VideoWeed
- **Vidme**
- **vidme**
- **vidme:user**
- **vidme:user:likes**
- **Vidzi**
- **vier**
- **vier:videos**
@@ -707,6 +738,7 @@
- **WebOfStories**
- **WebOfStoriesPlaylist**
- **Weibo**
- **WeiqiTV**: WQTV
- **wholecloud**: WholeCloud
- **Wimp**
- **Wistia**
@@ -758,3 +790,4 @@
- **ZDFChannel**
- **zingmp3:album**: mp3.zing.vn albums
- **zingmp3:song**: mp3.zing.vn songs
- **ZippCast**

View File

@@ -11,8 +11,11 @@ import sys
import youtube_dl.extractor
from youtube_dl import YoutubeDL
from youtube_dl.utils import (
from youtube_dl.compat import (
compat_os_name,
compat_str,
)
from youtube_dl.utils import (
preferredencoding,
write_string,
)
@@ -42,7 +45,7 @@ def report_warning(message):
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
'''
if sys.stderr.isatty() and os.name != 'nt':
if sys.stderr.isatty() and compat_os_name != 'nt':
_msg_header = '\033[0;33mWARNING:\033[0m'
else:
_msg_header = 'WARNING:'

View File

@@ -14,6 +14,7 @@ from test.helper import FakeYDL, assertRegexpMatches
from youtube_dl import YoutubeDL
from youtube_dl.compat import compat_str, compat_urllib_error
from youtube_dl.extractor import YoutubeIE
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.postprocessor.common import PostProcessor
from youtube_dl.utils import ExtractorError, match_filter_func
@@ -221,9 +222,19 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'dash-video-low')
formats = [
{'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL},
]
info_dict = _make_result(formats)
ydl = YDL({'format': 'bestvideo[vcodec=avc1.123456]'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
def test_youtube_format_selection(self):
order = [
'38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13',
'38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',
# Apple HTTP Live Streaming
'96', '95', '94', '93', '92', '132', '151',
# 3D
@@ -237,6 +248,17 @@ class TestFormatSelection(unittest.TestCase):
def format_info(f_id):
info = YoutubeIE._formats[f_id].copy()
# XXX: In real cases InfoExtractor._parse_mpd_formats() fills up 'acodec'
# and 'vcodec', while in tests such information is incomplete since
# commit a6c2c24479e5f4827ceb06f64d855329c0a6f593
# test_YoutubeDL.test_youtube_format_selection is broken without
# this fix
if 'acodec' in info and 'vcodec' not in info:
info['vcodec'] = 'none'
elif 'vcodec' in info and 'acodec' not in info:
info['acodec'] = 'none'
info['format_id'] = f_id
info['url'] = 'url:' + f_id
return info
@@ -636,6 +658,42 @@ class TestYoutubeDL(unittest.TestCase):
ydl = YDL()
self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd')
def test_do_not_override_ie_key_in_url_transparent(self):
ydl = YDL()
class Foo1IE(InfoExtractor):
_VALID_URL = r'foo1:'
def _real_extract(self, url):
return {
'_type': 'url_transparent',
'url': 'foo2:',
'ie_key': 'Foo2',
}
class Foo2IE(InfoExtractor):
_VALID_URL = r'foo2:'
def _real_extract(self, url):
return {
'_type': 'url',
'url': 'foo3:',
'ie_key': 'Foo3',
}
class Foo3IE(InfoExtractor):
_VALID_URL = r'foo3:'
def _real_extract(self, url):
return _make_result([{'url': TEST_URL}])
ydl.add_info_extractor(Foo1IE(ydl))
ydl.add_info_extractor(Foo2IE(ydl))
ydl.add_info_extractor(Foo3IE(ydl))
ydl.extract_info('foo1:')
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['url'], TEST_URL)
if __name__ == '__main__':
unittest.main()

View File

@@ -56,7 +56,7 @@ class TestAllURLsMatching(unittest.TestCase):
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
def test_youtube_user_matching(self):
self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
def test_youtube_feeds(self):
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])

View File

@@ -52,7 +52,12 @@ class TestHTTP(unittest.TestCase):
('localhost', 0), HTTPTestRequestHandler)
self.httpd.socket = ssl.wrap_socket(
self.httpd.socket, certfile=certfn, server_side=True)
self.port = self.httpd.socket.getsockname()[1]
if os.name == 'java':
# In Jython SSLSocket is not a subclass of socket.socket
sock = self.httpd.socket.sock
else:
sock = self.httpd.socket
self.port = sock.getsockname()[1]
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
self.server_thread.start()

View File

@@ -0,0 +1,47 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
from youtube_dl.extractor import IqiyiIE
class IqiyiIEWithCredentials(IqiyiIE):
def _get_login_info(self):
return 'foo', 'bar'
class WarningLogger(object):
def __init__(self):
self.messages = []
def warning(self, msg):
self.messages.append(msg)
def debug(self, msg):
pass
def error(self, msg):
pass
class TestIqiyiSDKInterpreter(unittest.TestCase):
def test_iqiyi_sdk_interpreter(self):
'''
Test the functionality of IqiyiSDKInterpreter by trying to log in
If `sign` is incorrect, /validate call throws an HTTP 556 error
'''
logger = WarningLogger()
ie = IqiyiIEWithCredentials(FakeYDL({'logger': logger}))
ie._login()
self.assertTrue('unable to log in:' in logger.messages[0])
if __name__ == '__main__':
unittest.main()

View File

@@ -21,7 +21,7 @@ from youtube_dl.extractor import (
NPOIE,
ComedyCentralIE,
NRKTVIE,
RaiIE,
RaiTVIE,
VikiIE,
ThePlatformIE,
ThePlatformFeedIE,
@@ -65,16 +65,16 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 13)
self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
for lang in ['it', 'fr', 'de']:
self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
self.assertEqual(md5(subtitles['it']), '6d752b98c31f1cf8d597050c7a2cb4b5')
for lang in ['fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
def test_youtube_subtitles_sbv_format(self):
def test_youtube_subtitles_ttml_format(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitlesformat'] = 'sbv'
self.DL.params['subtitlesformat'] = 'ttml'
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b')
self.assertEqual(md5(subtitles['en']), 'e306f8c42842f723447d9f63ad65df54')
def test_youtube_subtitles_vtt_format(self):
self.DL.params['writesubtitles'] = True
@@ -260,7 +260,7 @@ class TestNRKSubtitles(BaseTestSubtitles):
class TestRaiSubtitles(BaseTestSubtitles):
url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
IE = RaiIE
IE = RaiTVIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True

30
test/test_update.py Normal file
View File

@@ -0,0 +1,30 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import json
from youtube_dl.update import rsa_verify
class TestUpdate(unittest.TestCase):
def test_rsa_verify(self):
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'versions.json'), 'rb') as f:
versions_info = f.read().decode()
versions_info = json.loads(versions_info)
signature = versions_info['signature']
del versions_info['signature']
self.assertTrue(rsa_verify(
json.dumps(versions_info, sort_keys=True).encode('utf-8'),
signature, UPDATES_RSA_KEY))
if __name__ == '__main__':
unittest.main()

View File

@@ -18,10 +18,12 @@ import xml.etree.ElementTree
from youtube_dl.utils import (
age_restricted,
args_to_str,
encode_base_n,
clean_html,
DateRange,
detect_exe_version,
determine_ext,
dict_get,
encode_compat_str,
encodeFilename,
escape_rfc3986,
@@ -34,6 +36,7 @@ from youtube_dl.utils import (
is_html,
js_to_json,
limit_length,
ohdave_rsa_encrypt,
OnDemandPagedList,
orderedSet,
parse_duration,
@@ -58,6 +61,7 @@ from youtube_dl.utils import (
lowercase_escape,
url_basename,
urlencode_postdata,
update_url_query,
version_tuple,
xpath_with_ns,
xpath_element,
@@ -73,6 +77,8 @@ from youtube_dl.utils import (
)
from youtube_dl.compat import (
compat_etree_fromstring,
compat_urlparse,
compat_parse_qs,
)
@@ -247,6 +253,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
self.assertEqual(unified_strdate('25-09-2014'), '20140925')
self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
@@ -450,6 +457,62 @@ class TestUtil(unittest.TestCase):
data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
self.assertTrue(isinstance(data, bytes))
def test_update_url_query(self):
def query_dict(url):
return compat_parse_qs(compat_urlparse.urlparse(url).query)
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
query_dict('http://example.com/path?quality=HD&format=mp4'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'fields': 'id,formats,subtitles'})),
query_dict('http://example.com/path?fields=id,formats,subtitles'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path?manifest=f4m', {'manifest': []})),
query_dict('http://example.com/path'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
query_dict('http://example.com/path?system=LINUX'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'fields': b'id,formats,subtitles'})),
query_dict('http://example.com/path?fields=id,formats,subtitles'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'width': 1080, 'height': 720})),
query_dict('http://example.com/path?width=1080&height=720'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'bitrate': 5020.43})),
query_dict('http://example.com/path?bitrate=5020.43'))
self.assertEqual(query_dict(update_url_query(
'http://example.com/path', {'test': '第二行тест'})),
query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
def test_dict_get(self):
FALSE_VALUES = {
'none': None,
'false': False,
'zero': 0,
'empty_string': '',
'empty_list': [],
}
d = FALSE_VALUES.copy()
d['a'] = 42
self.assertEqual(dict_get(d, 'a'), 42)
self.assertEqual(dict_get(d, 'b'), None)
self.assertEqual(dict_get(d, 'b', 42), 42)
self.assertEqual(dict_get(d, ('a', )), 42)
self.assertEqual(dict_get(d, ('b', 'a', )), 42)
self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
self.assertEqual(dict_get(d, ('b', 'c', )), None)
self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
for key, false_value in FALSE_VALUES.items():
self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
def test_encode_compat_str(self):
self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
@@ -471,6 +534,10 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'STATUS': 'OK'})
stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape(''), '')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@@ -765,6 +832,24 @@ The first line
{'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
['--check-certificate=true'])
def test_ohdave_rsa_encrypt(self):
N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
e = 65537
self.assertEqual(
ohdave_rsa_encrypt(b'aa111222', e, N),
'726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
def test_encode_base_n(self):
self.assertEqual(encode_base_n(0, 30), '0')
self.assertEqual(encode_base_n(80, 30), '2k')
custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
self.assertEqual(encode_base_n(0, 30, custom_table), '9')
self.assertEqual(encode_base_n(80, 30, custom_table), '7P')
self.assertRaises(ValueError, encode_base_n, 0, 70)
self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
if __name__ == '__main__':
unittest.main()

View File

@@ -34,7 +34,7 @@ class TestYoutubeLists(unittest.TestCase):
ie = YoutubePlaylistIE(dl)
# TODO find a > 100 (paginating?) videos course
result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
entries = result['entries']
entries = list(result['entries'])
self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
self.assertEqual(len(entries), 25)
self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')

34
test/versions.json Normal file
View File

@@ -0,0 +1,34 @@
{
"latest": "2013.01.06",
"signature": "72158cdba391628569ffdbea259afbcf279bbe3d8aeb7492690735dc1cfa6afa754f55c61196f3871d429599ab22f2667f1fec98865527b32632e7f4b3675a7ef0f0fbe084d359256ae4bba68f0d33854e531a70754712f244be71d4b92e664302aa99653ee4df19800d955b6c4149cd2b3f24288d6e4b40b16126e01f4c8ce6",
"versions": {
"2013.01.02": {
"bin": [
"http://youtube-dl.org/downloads/2013.01.02/youtube-dl",
"f5b502f8aaa77675c4884938b1e4871ebca2611813a0c0e74f60c0fbd6dcca6b"
],
"exe": [
"http://youtube-dl.org/downloads/2013.01.02/youtube-dl.exe",
"75fa89d2ce297d102ff27675aa9d92545bbc91013f52ec52868c069f4f9f0422"
],
"tar": [
"http://youtube-dl.org/downloads/2013.01.02/youtube-dl-2013.01.02.tar.gz",
"6a66d022ac8e1c13da284036288a133ec8dba003b7bd3a5179d0c0daca8c8196"
]
},
"2013.01.06": {
"bin": [
"http://youtube-dl.org/downloads/2013.01.06/youtube-dl",
"64b6ed8865735c6302e836d4d832577321b4519aa02640dc508580c1ee824049"
],
"exe": [
"http://youtube-dl.org/downloads/2013.01.06/youtube-dl.exe",
"58609baf91e4389d36e3ba586e21dab882daaaee537e4448b1265392ae86ff84"
],
"tar": [
"http://youtube-dl.org/downloads/2013.01.06/youtube-dl-2013.01.06.tar.gz",
"fe77ab20a95d980ed17a659aa67e371fdd4d656d19c4c7950e7b720b0c2f1a86"
]
}
}
}

View File

@@ -24,9 +24,6 @@ import time
import tokenize
import traceback
if os.name == 'nt':
import ctypes
from .compat import (
compat_basestring,
compat_cookiejar,
@@ -34,6 +31,7 @@ from .compat import (
compat_get_terminal_size,
compat_http_client,
compat_kwargs,
compat_os_name,
compat_str,
compat_tokenize_tokenize,
compat_urllib_error,
@@ -46,6 +44,7 @@ from .utils import (
DateRange,
DEFAULT_OUTTMPL,
determine_ext,
determine_protocol,
DownloadError,
encode_compat_str,
encodeFilename,
@@ -86,6 +85,7 @@ from .extractor import get_info_extractor, gen_extractors
from .downloader import get_suitable_downloader
from .downloader.rtmp import rtmpdump_version
from .postprocessor import (
FFmpegFixupM3u8PP,
FFmpegFixupM4aPP,
FFmpegFixupStretchedPP,
FFmpegMergerPP,
@@ -94,6 +94,9 @@ from .postprocessor import (
)
from .version import __version__
if compat_os_name == 'nt':
import ctypes
class YoutubeDL(object):
"""YoutubeDL class.
@@ -262,7 +265,7 @@ class YoutubeDL(object):
the downloader (see youtube_dl/downloader/common.py):
nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
noresizebuffer, retries, continuedl, noprogress, consoletitle,
xattr_set_filesize, external_downloader_args.
xattr_set_filesize, external_downloader_args, hls_use_mpegts.
The following options are used by the post processors:
prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available,
@@ -449,7 +452,7 @@ class YoutubeDL(object):
def to_console_title(self, message):
if not self.params.get('consoletitle', False):
return
if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
if compat_os_name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
# c_wchar_p() might not be necessary if `message` is
# already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
@@ -520,7 +523,7 @@ class YoutubeDL(object):
else:
if self.params.get('no_warnings'):
return
if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':
if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt':
_msg_header = '\033[0;33mWARNING:\033[0m'
else:
_msg_header = 'WARNING:'
@@ -532,7 +535,7 @@ class YoutubeDL(object):
Do the same as trouble, but prefixes the message with 'ERROR:', colored
in red if stderr is a tty file.
'''
if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':
if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt':
_msg_header = '\033[0;31mERROR:\033[0m'
else:
_msg_header = 'ERROR:'
@@ -565,7 +568,7 @@ class YoutubeDL(object):
elif template_dict.get('height'):
template_dict['resolution'] = '%sp' % template_dict['height']
elif template_dict.get('width'):
template_dict['resolution'] = '?x%d' % template_dict['width']
template_dict['resolution'] = '%dx?' % template_dict['width']
sanitize = lambda k, v: sanitize_filename(
compat_str(v),
@@ -604,12 +607,12 @@ class YoutubeDL(object):
if rejecttitle:
if re.search(rejecttitle, title, re.IGNORECASE):
return '"' + title + '" title matched reject pattern "' + rejecttitle + '"'
date = info_dict.get('upload_date', None)
date = info_dict.get('upload_date')
if date is not None:
dateRange = self.params.get('daterange', DateRange())
if date not in dateRange:
return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
view_count = info_dict.get('view_count', None)
view_count = info_dict.get('view_count')
if view_count is not None:
min_views = self.params.get('min_views')
if min_views is not None and view_count < min_views:
@@ -706,7 +709,6 @@ class YoutubeDL(object):
It will also download the videos if 'download'.
Returns the resolved ie_result.
"""
result_type = ie_result.get('_type', 'video')
if result_type in ('url', 'url_transparent'):
@@ -735,7 +737,7 @@ class YoutubeDL(object):
force_properties = dict(
(k, v) for k, v in ie_result.items() if v is not None)
for f in ('_type', 'url'):
for f in ('_type', 'url', 'ie_key'):
if f in force_properties:
del force_properties[f]
new_result = info.copy()
@@ -747,18 +749,18 @@ class YoutubeDL(object):
new_result, download=download, extra_info=extra_info)
elif result_type == 'playlist' or result_type == 'multi_video':
# We process each entry in the playlist
playlist = ie_result.get('title', None) or ie_result.get('id', None)
playlist = ie_result.get('title') or ie_result.get('id')
self.to_screen('[download] Downloading playlist: %s' % playlist)
playlist_results = []
playliststart = self.params.get('playliststart', 1) - 1
playlistend = self.params.get('playlistend', None)
playlistend = self.params.get('playlistend')
# For backwards compatibility, interpret -1 as whole list
if playlistend == -1:
playlistend = None
playlistitems_str = self.params.get('playlist_items', None)
playlistitems_str = self.params.get('playlist_items')
playlistitems = None
if playlistitems_str is not None:
def iter_playlistitems(format):
@@ -782,7 +784,7 @@ class YoutubeDL(object):
entries = ie_entries[playliststart:playlistend]
n_entries = len(entries)
self.to_screen(
"[%s] playlist %s: Collected %d video ids (downloading %d of them)" %
'[%s] playlist %s: Collected %d video ids (downloading %d of them)' %
(ie_result['extractor'], playlist, n_all_entries, n_entries))
elif isinstance(ie_entries, PagedList):
if playlistitems:
@@ -796,7 +798,7 @@ class YoutubeDL(object):
playliststart, playlistend)
n_entries = len(entries)
self.to_screen(
"[%s] playlist %s: Downloading %d videos" %
'[%s] playlist %s: Downloading %d videos' %
(ie_result['extractor'], playlist, n_entries))
else: # iterable
if playlistitems:
@@ -807,7 +809,7 @@ class YoutubeDL(object):
ie_entries, playliststart, playlistend))
n_entries = len(entries)
self.to_screen(
"[%s] playlist %s: Downloading %d videos" %
'[%s] playlist %s: Downloading %d videos' %
(ie_result['extractor'], playlist, n_entries))
if self.params.get('playlistreverse', False):
@@ -898,11 +900,14 @@ class YoutubeDL(object):
STR_OPERATORS = {
'=': operator.eq,
'!=': operator.ne,
'^=': lambda attr, value: attr.startswith(value),
'$=': lambda attr, value: attr.endswith(value),
'*=': lambda attr, value: value in attr,
}
str_operator_rex = re.compile(r'''(?x)
\s*(?P<key>ext|acodec|vcodec|container|protocol)
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
\s*(?P<value>[a-zA-Z0-9_-]+)
\s*(?P<value>[a-zA-Z0-9._-]+)
\s*$
''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
m = str_operator_rex.search(filter_spec)
@@ -1244,6 +1249,12 @@ class YoutubeDL(object):
except (ValueError, OverflowError, OSError):
pass
# Auto generate title fields corresponding to the *_number fields when missing
# in order to always have clean titles. This is very common for TV series.
for field in ('chapter', 'season', 'episode'):
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
subtitles = info_dict.get('subtitles')
if subtitles:
for _, subtitle in subtitles.items():
@@ -1279,6 +1290,9 @@ class YoutubeDL(object):
if format.get('format_id') is None:
format['format_id'] = compat_str(i)
else:
# Sanitize format_id from characters used in format selector expression
format['format_id'] = re.sub('[\s,/+\[\]()]', '_', format['format_id'])
format_id = format['format_id']
if format_id not in formats_dict:
formats_dict[format_id] = []
@@ -1300,6 +1314,10 @@ class YoutubeDL(object):
# Automatically determine file extension if missing
if 'ext' not in format:
format['ext'] = determine_ext(format['url']).lower()
# Automatically determine protocol if missing (useful for format
# selection purposes)
if 'protocol' not in format:
format['protocol'] = determine_protocol(format)
# Add HTTP headers, so that external programs can use them from the
# json output
full_format_info = info_dict.copy()
@@ -1325,7 +1343,6 @@ class YoutubeDL(object):
if req_format is None:
req_format_list = []
if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-' and
info_dict['extractor'] in ['youtube', 'ted'] and
not info_dict.get('is_live')):
merger = FFmpegMergerPP(self)
if merger.available and merger.can_merge():
@@ -1616,12 +1633,14 @@ class YoutubeDL(object):
self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
if success:
if success and filename != '-':
# Fixup content
fixup_policy = self.params.get('fixup')
if fixup_policy is None:
fixup_policy = 'detect_or_warn'
INSTALL_FFMPEG_MESSAGE = 'Install ffmpeg or avconv to fix this automatically.'
stretched_ratio = info_dict.get('stretched_ratio')
if stretched_ratio is not None and stretched_ratio != 1:
if fixup_policy == 'warn':
@@ -1634,15 +1653,18 @@ class YoutubeDL(object):
info_dict['__postprocessors'].append(stretched_pp)
else:
self.report_warning(
'%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % (
info_dict['id'], stretched_ratio))
'%s: Non-uniform pixel ratio (%s). %s'
% (info_dict['id'], stretched_ratio, INSTALL_FFMPEG_MESSAGE))
else:
assert fixup_policy in ('ignore', 'never')
if info_dict.get('requested_formats') is None and info_dict.get('container') == 'm4a_dash':
if (info_dict.get('requested_formats') is None and
info_dict.get('container') == 'm4a_dash'):
if fixup_policy == 'warn':
self.report_warning('%s: writing DASH m4a. Only some players support this container.' % (
info_dict['id']))
self.report_warning(
'%s: writing DASH m4a. '
'Only some players support this container.'
% info_dict['id'])
elif fixup_policy == 'detect_or_warn':
fixup_pp = FFmpegFixupM4aPP(self)
if fixup_pp.available:
@@ -1650,8 +1672,27 @@ class YoutubeDL(object):
info_dict['__postprocessors'].append(fixup_pp)
else:
self.report_warning(
'%s: writing DASH m4a. Only some players support this container. Install ffmpeg or avconv to fix this automatically.' % (
info_dict['id']))
'%s: writing DASH m4a. '
'Only some players support this container. %s'
% (info_dict['id'], INSTALL_FFMPEG_MESSAGE))
else:
assert fixup_policy in ('ignore', 'never')
if (info_dict.get('protocol') == 'm3u8_native' or
info_dict.get('protocol') == 'm3u8' and
self.params.get('hls_prefer_native')):
if fixup_policy == 'warn':
self.report_warning('%s: malformated aac bitstream.' % (
info_dict['id']))
elif fixup_policy == 'detect_or_warn':
fixup_pp = FFmpegFixupM3u8PP(self)
if fixup_pp.available:
info_dict.setdefault('__postprocessors', [])
info_dict['__postprocessors'].append(fixup_pp)
else:
self.report_warning(
'%s: malformated aac bitstream. %s'
% (info_dict['id'], INSTALL_FFMPEG_MESSAGE))
else:
assert fixup_policy in ('ignore', 'never')
@@ -1782,7 +1823,7 @@ class YoutubeDL(object):
else:
res = '%sp' % format['height']
elif format.get('width') is not None:
res = '?x%d' % format['width']
res = '%dx?' % format['width']
else:
res = default
return res

View File

@@ -355,6 +355,7 @@ def _real_main(argv=None):
'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
'encoding': opts.encoding,
'extract_flat': opts.extract_flat,
'mark_watched': opts.mark_watched,
'merge_output_format': opts.merge_output_format,
'postprocessors': postprocessors,
'fixup': opts.fixup,
@@ -369,6 +370,7 @@ def _real_main(argv=None):
'no_color': opts.no_color,
'ffmpeg_location': opts.ffmpeg_location,
'hls_prefer_native': opts.hls_prefer_native,
'hls_use_mpegts': opts.hls_use_mpegts,
'external_downloader_args': external_downloader_args,
'postprocessor_args': postprocessor_args,
'cn_verification_proxy': opts.cn_verification_proxy,

View File

@@ -7,7 +7,7 @@ from __future__ import unicode_literals
import sys
if __package__ is None and not hasattr(sys, "frozen"):
if __package__ is None and not hasattr(sys, 'frozen'):
# direct call of __main__.py
import os.path
path = os.path.realpath(os.path.abspath(__file__))

View File

@@ -161,7 +161,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
nonce = data[:NONCE_LENGTH_BYTES]
cipher = data[NONCE_LENGTH_BYTES:]
class Counter:
class Counter(object):
__value = nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
def next_value(self):

View File

@@ -181,20 +181,20 @@ except ImportError: # Python < 3.4
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(":", 1)
mediatype, data = data.split(",", 1)
scheme, data = url.split(':', 1)
mediatype, data = data.split(',', 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(";base64"):
if mediatype.endswith(';base64'):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = "text/plain;charset=US-ASCII"
mediatype = 'text/plain;charset=US-ASCII'
headers = email.message_from_string(
"Content-type: %s\nContent-length: %d\n" % (mediatype, len(data)))
'Content-type: %s\nContent-length: %d\n' % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
@@ -268,7 +268,7 @@ except ImportError: # Python 2
nv = name_value.split('=', 1)
if len(nv) != 2:
if strict_parsing:
raise ValueError("bad query field: %r" % (name_value,))
raise ValueError('bad query field: %r' % (name_value,))
# Handle case of a control-name with no equal sign
if keep_blank_values:
nv.append('')
@@ -326,6 +326,9 @@ def compat_ord(c):
return ord(c)
compat_os_name = os._name if os.name == 'java' else os.name
if sys.version_info >= (3, 0):
compat_getenv = os.getenv
compat_expanduser = os.path.expanduser
@@ -346,7 +349,7 @@ else:
# The following are os.path.expanduser implementations from cpython 2.7.8 stdlib
# for different platforms with correct environment variables decoding.
if os.name == 'posix':
if compat_os_name == 'posix':
def compat_expanduser(path):
"""Expand ~ and ~user constructions. If user or $HOME is unknown,
do nothing."""
@@ -370,7 +373,7 @@ else:
userhome = pwent.pw_dir
userhome = userhome.rstrip('/')
return (userhome + path[i:]) or '/'
elif os.name == 'nt' or os.name == 'ce':
elif compat_os_name == 'nt' or compat_os_name == 'ce':
def compat_expanduser(path):
"""Expand ~ and ~user constructs.
@@ -433,7 +436,7 @@ if sys.version_info < (3, 0) and sys.platform == 'win32':
else:
compat_getpass = getpass.getpass
# Old 2.6 and 2.7 releases require kwargs to be bytes
# Python < 2.6.5 require kwargs to be bytes
try:
def _testfunc(x):
pass
@@ -466,7 +469,7 @@ if sys.version_info < (2, 7):
if err is not None:
raise err
else:
raise socket.error("getaddrinfo returns an empty list")
raise socket.error('getaddrinfo returns an empty list')
else:
compat_socket_create_connection = socket.create_connection
@@ -556,6 +559,7 @@ __all__ = [
'compat_itertools_count',
'compat_kwargs',
'compat_ord',
'compat_os_name',
'compat_parse_qs',
'compat_print',
'compat_shlex_split',

View File

@@ -5,6 +5,7 @@ import re
import sys
import time
from ..compat import compat_os_name
from ..utils import (
encodeFilename,
error_to_compat_str,
@@ -45,6 +46,7 @@ class FileDownloader(object):
(experimental)
external_downloader_args: A list of additional command-line arguments for the
external downloader.
hls_use_mpegts: Use the mpegts container for HLS videos.
Subclasses of this one must re-define the real_download method.
"""
@@ -156,7 +158,7 @@ class FileDownloader(object):
def slow_down(self, start_time, now, byte_counter):
"""Sleep if the download speed is over the rate limit."""
rate_limit = self.params.get('ratelimit', None)
rate_limit = self.params.get('ratelimit')
if rate_limit is None or byte_counter == 0:
return
if now is None:
@@ -218,7 +220,7 @@ class FileDownloader(object):
if self.params.get('progress_with_newline', False):
self.to_screen(fullmsg)
else:
if os.name == 'nt':
if compat_os_name == 'nt':
prev_len = getattr(self, '_report_progress_prev_line_length',
0)
if prev_len > len(fullmsg):
@@ -295,7 +297,7 @@ class FileDownloader(object):
def report_retry(self, count, retries):
"""Report retry in case of HTTP error 5xx"""
self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %.0f)...' % (count, retries))
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""

View File

@@ -1,66 +1,59 @@
from __future__ import unicode_literals
import os
import re
from .common import FileDownloader
from ..utils import sanitized_Request
from .fragment import FragmentFD
from ..utils import (
sanitize_open,
encodeFilename,
)
class DashSegmentsFD(FileDownloader):
class DashSegmentsFD(FragmentFD):
"""
Download segments in a DASH manifest
"""
FD_NAME = 'dashsegments'
def real_download(self, filename, info_dict):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
base_url = info_dict['url']
segment_urls = info_dict['segment_urls']
segment_urls = [info_dict['segment_urls'][0]] if self.params.get('test', False) else info_dict['segment_urls']
initialization_url = info_dict.get('initialization_url')
is_test = self.params.get('test', False)
remaining_bytes = self._TEST_FILE_SIZE if is_test else None
byte_counter = 0
ctx = {
'filename': filename,
'total_frags': len(segment_urls) + (1 if initialization_url else 0),
}
def append_url_to_file(outf, target_url, target_name, remaining_bytes=None):
self.to_screen('[DashSegments] %s: Downloading %s' % (info_dict['id'], target_name))
req = sanitized_Request(target_url)
if remaining_bytes is not None:
req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
data = self.ydl.urlopen(req).read()
if remaining_bytes is not None:
data = data[:remaining_bytes]
outf.write(data)
return len(data)
self._prepare_and_start_frag_download(ctx)
def combine_url(base_url, target_url):
if re.match(r'^https?://', target_url):
return target_url
return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
with open(tmpfilename, 'wb') as outf:
append_url_to_file(
outf, combine_url(base_url, info_dict['initialization_url']),
'initialization segment')
for i, segment_url in enumerate(segment_urls):
segment_len = append_url_to_file(
outf, combine_url(base_url, segment_url),
'segment %d / %d' % (i + 1, len(segment_urls)),
remaining_bytes)
byte_counter += segment_len
if remaining_bytes is not None:
remaining_bytes -= segment_len
if remaining_bytes <= 0:
break
segments_filenames = []
self.try_rename(tmpfilename, filename)
def append_url_to_file(target_url, target_filename):
success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)})
if not success:
return False
down, target_sanitized = sanitize_open(target_filename, 'rb')
ctx['dest_stream'].write(down.read())
down.close()
segments_filenames.append(target_sanitized)
self._hook_progress({
'downloaded_bytes': byte_counter,
'total_bytes': byte_counter,
'filename': filename,
'status': 'finished',
})
if initialization_url:
append_url_to_file(initialization_url, ctx['tmpfilename'] + '-Init')
for i, segment_url in enumerate(segment_urls):
segment_filename = '%s-Seg%d' % (ctx['tmpfilename'], i)
append_url_to_file(segment_url, segment_filename)
self._finish_frag_download(ctx)
for segment_file in segments_filenames:
os.remove(encodeFilename(segment_file))
return True

View File

@@ -273,15 +273,21 @@ class F4mFD(FragmentFD):
return fragments_list
def _parse_bootstrap_node(self, node, base_url):
if node.text is None:
# Sometimes non empty inline bootstrap info can be specified along
# with bootstrap url attribute (e.g. dummy inline bootstrap info
# contains whitespace characters in [1]). We will prefer bootstrap
# url over inline bootstrap info when present.
# 1. http://live-1-1.rutube.ru/stream/1024/HDS/SD/C2NKsS85HQNckgn5HdEmOQ/1454167650/S-s604419906/move/four/dirs/upper/1024-576p.f4m
bootstrap_url = node.get('url')
if bootstrap_url:
bootstrap_url = compat_urlparse.urljoin(
base_url, node.attrib['url'])
base_url, bootstrap_url)
boot_info = self._get_bootstrap_from_url(bootstrap_url)
else:
bootstrap_url = None
bootstrap = base64.b64decode(node.text.encode('ascii'))
boot_info = read_bootstrap_info(bootstrap)
return (boot_info, bootstrap_url)
return boot_info, bootstrap_url
def real_download(self, filename, info_dict):
man_url = info_dict['url']
@@ -316,7 +322,8 @@ class F4mFD(FragmentFD):
metadata = None
fragments_list = build_fragments_list(boot_info)
if self.params.get('test', False):
test = self.params.get('test', False)
if test:
# We only download the first fragment
fragments_list = fragments_list[:1]
total_frags = len(fragments_list)
@@ -326,6 +333,7 @@ class F4mFD(FragmentFD):
ctx = {
'filename': filename,
'total_frags': total_frags,
'live': live,
}
self._prepare_frag_download(ctx)
@@ -380,7 +388,7 @@ class F4mFD(FragmentFD):
else:
raise
if not fragments_list and live and bootstrap_url:
if not fragments_list and not test and live and bootstrap_url:
fragments_list = self._update_live_fragments(bootstrap_url, frag_i)
total_frags += len(fragments_list)
if fragments_list and (fragments_list[0][1] > frag_i + 1):

View File

@@ -26,7 +26,11 @@ class FragmentFD(FileDownloader):
self._start_frag_download(ctx)
def _prepare_frag_download(self, ctx):
self.to_screen('[%s] Total fragments: %d' % (self.FD_NAME, ctx['total_frags']))
if 'live' not in ctx:
ctx['live'] = False
self.to_screen(
'[%s] Total fragments: %s'
% (self.FD_NAME, ctx['total_frags'] if not ctx['live'] else 'unknown (live)'))
self.report_destination(ctx['filename'])
dl = HttpQuietDownloader(
self.ydl,
@@ -34,7 +38,7 @@ class FragmentFD(FileDownloader):
'continuedl': True,
'quiet': True,
'noprogress': True,
'ratelimit': self.params.get('ratelimit', None),
'ratelimit': self.params.get('ratelimit'),
'retries': self.params.get('retries', 0),
'test': self.params.get('test', False),
}
@@ -74,14 +78,14 @@ class FragmentFD(FileDownloader):
if s['status'] not in ('downloading', 'finished'):
return
frag_total_bytes = s.get('total_bytes') or 0
estimated_size = (
(ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
(state['frag_index'] + 1) * total_frags)
time_now = time.time()
state['total_bytes_estimate'] = estimated_size
state['elapsed'] = time_now - start
frag_total_bytes = s.get('total_bytes') or 0
if not ctx['live']:
estimated_size = (
(ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
(state['frag_index'] + 1) * total_frags)
state['total_bytes_estimate'] = estimated_size
if s['status'] == 'finished':
state['frag_index'] += 1
@@ -91,10 +95,12 @@ class FragmentFD(FileDownloader):
else:
frag_downloaded_bytes = s['downloaded_bytes']
state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes']
state['eta'] = self.calc_eta(
start, time_now, estimated_size,
state['downloaded_bytes'])
state['speed'] = s.get('speed')
if not ctx['live']:
state['eta'] = self.calc_eta(
start, time_now, estimated_size,
state['downloaded_bytes'])
state['speed'] = s.get('speed') or ctx.get('speed')
ctx['speed'] = state['speed']
ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes
self._hook_progress(state)

View File

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
import os
import re
import subprocess
import sys
from .common import FileDownloader
from .fragment import FragmentFD
@@ -39,14 +40,29 @@ class HlsFD(FileDownloader):
'-headers',
''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
args += ['-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc']
args += ['-i', url, '-c', 'copy']
if self.params.get('hls_use_mpegts', False):
args += ['-f', 'mpegts']
else:
args += ['-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
args = [encodeArgument(opt) for opt in args]
args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
self._debug_cmd(args)
retval = subprocess.call(args, stdin=subprocess.PIPE)
proc = subprocess.Popen(args, stdin=subprocess.PIPE)
try:
retval = proc.wait()
except KeyboardInterrupt:
# subprocces.run would send the SIGKILL signal to ffmpeg and the
# mp4 file couldn't be played, but if we ask ffmpeg to quit it
# produces a file that is playable (this is mostly useful for live
# streams). Note that Windows is not affected and produces playable
# files (see https://github.com/rg3/youtube-dl/issues/8300).
if sys.platform != 'win32':
proc.communicate(b'q')
raise
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] %s bytes' % (args[0], fsize))

View File

@@ -140,8 +140,8 @@ class HttpFD(FileDownloader):
if data_len is not None:
data_len = int(data_len) + resume_len
min_data_len = self.params.get("min_filesize", None)
max_data_len = self.params.get("max_filesize", None)
min_data_len = self.params.get('min_filesize')
max_data_len = self.params.get('max_filesize')
if min_data_len is not None and data_len < min_data_len:
self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
return False

View File

@@ -94,15 +94,15 @@ class RtmpFD(FileDownloader):
return proc.returncode
url = info_dict['url']
player_url = info_dict.get('player_url', None)
page_url = info_dict.get('page_url', None)
app = info_dict.get('app', None)
play_path = info_dict.get('play_path', None)
tc_url = info_dict.get('tc_url', None)
flash_version = info_dict.get('flash_version', None)
player_url = info_dict.get('player_url')
page_url = info_dict.get('page_url')
app = info_dict.get('app')
play_path = info_dict.get('play_path')
tc_url = info_dict.get('tc_url')
flash_version = info_dict.get('flash_version')
live = info_dict.get('rtmp_live', False)
conn = info_dict.get('rtmp_conn', None)
protocol = info_dict.get('rtmp_protocol', None)
conn = info_dict.get('rtmp_conn')
protocol = info_dict.get('rtmp_protocol')
real_time = info_dict.get('rtmp_real_time', False)
no_resume = info_dict.get('no_resume', False)
continue_dl = self.params.get('continuedl', True)

View File

@@ -15,14 +15,18 @@ from .adobetv import (
AdobeTVVideoIE,
)
from .adultswim import AdultSwimIE
from .ae import AEIE
from .aenetworks import AENetworksIE
from .aftonbladet import AftonbladetIE
from .airmozilla import AirMozillaIE
from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE
from .animeondemand import AnimeOnDemandIE
from .anitube import AnitubeIE
from .anysex import AnySexIE
from .aol import AolIE
from .aol import (
AolIE,
AolFeaturesIE,
)
from .allocine import AllocineIE
from .aparat import AparatIE
from .appleconnect import AppleConnectIE
@@ -42,14 +46,16 @@ from .arte import (
ArteTVCreativeIE,
ArteTVConcertIE,
ArteTVFutureIE,
ArteTVCinemaIE,
ArteTVDDCIE,
ArteTVMagazineIE,
ArteTVEmbedIE,
)
from .atresplayer import AtresPlayerIE
from .atttechchannel import ATTTechChannelIE
from .audimedia import AudiMediaIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
from .azubu import AzubuIE
from .azubu import AzubuIE, AzubuLiveIE
from .baidu import BaiduVideoIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
@@ -71,6 +77,7 @@ from .bleacherreport import (
)
from .blinkx import BlinkxIE
from .bloomberg import BloombergIE
from .bokecc import BokeCCIE
from .bpb import BpbIE
from .br import BRIE
from .breakcom import BreakIE
@@ -88,8 +95,15 @@ from .camdemy import (
from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE
from .canvas import CanvasIE
from .cbc import (
CBCIE,
CBCPlayerIE,
)
from .cbs import CBSIE
from .cbsnews import CBSNewsIE
from .cbsnews import (
CBSNewsIE,
CBSNewsLiveVideoIE,
)
from .cbssports import CBSSportsIE
from .ccc import CCCIE
from .ceskatelevize import CeskaTelevizeIE
@@ -122,6 +136,7 @@ from .comcarcoff import ComCarCoffIE
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .condenast import CondeNastIE
from .cracked import CrackedIE
from .crackle import CrackleIE
from .criterion import CriterionIE
from .crooksandliars import CrooksAndLiarsIE
from .crunchyroll import (
@@ -130,6 +145,7 @@ from .crunchyroll import (
)
from .cspan import CSpanIE
from .ctsnews import CtsNewsIE
from .cultureunplugged import CultureUnpluggedIE
from .cwtv import CWTVIE
from .dailymotion import (
DailymotionIE,
@@ -140,6 +156,8 @@ from .dailymotion import (
from .daum import (
DaumIE,
DaumClipIE,
DaumPlaylistIE,
DaumUserIE,
)
from .dbtv import DBTVIE
from .dcn import (
@@ -194,7 +212,10 @@ from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE
from .expotv import ExpoTVIE
from .extremetube import ExtremeTubeIE
from .facebook import FacebookIE
from .facebook import (
FacebookIE,
FacebookPostIE,
)
from .faz import FazIE
from .fc2 import FC2IE
from .fczenit import FczenitIE
@@ -318,9 +339,11 @@ from .keezmovies import KeezMoviesIE
from .khanacademy import KhanAcademyIE
from .kickstarter import KickStarterIE
from .keek import KeekIE
from .konserthusetplay import KonserthusetPlayIE
from .kontrtube import KontrTubeIE
from .krasview import KrasViewIE
from .ku6 import Ku6IE
from .kusi import KUSIIE
from .kuwo import (
KuwoIE,
KuwoAlbumIE,
@@ -332,10 +355,11 @@ from .kuwo import (
from .la7 import LA7IE
from .laola1tv import Laola1TvIE
from .lecture2go import Lecture2GoIE
from .letv import (
LetvIE,
LetvTvIE,
LetvPlaylistIE
from .lemonde import LemondeIE
from .leeco import (
LeIE,
LePlaylistIE,
LetvCloudIE,
)
from .libsyn import LibsynIE
from .lifenews import (
@@ -354,6 +378,7 @@ from .livestream import (
LivestreamShortenerIE,
)
from .lnkgo import LnkGoIE
from .lovehomeporn import LoveHomePornIE
from .lrt import LRTIE
from .lynda import (
LyndaIE,
@@ -364,6 +389,7 @@ from .macgamestore import MacGameStoreIE
from .mailru import MailRuIE
from .makertv import MakerTVIE
from .malemotion import MalemotionIE
from .matchtv import MatchTVIE
from .mdr import MDRIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
@@ -469,11 +495,13 @@ from .nowtv import (
NowTVIE,
NowTVListIE,
)
from .noz import NozIE
from .npo import (
NPOIE,
NPOLiveIE,
NPORadioIE,
NPORadioFragmentIE,
SchoolTVIE,
VPROIE,
WNLIE
)
@@ -481,6 +509,7 @@ from .npr import NprIE
from .nrk import (
NRKIE,
NRKPlaylistIE,
NRKSkoleIE,
NRKTVIE,
)
from .ntvde import NTVDeIE
@@ -517,6 +546,7 @@ from .planetaplay import PlanetaPlayIE
from .pladform import PladformIE
from .played import PlayedIE
from .playfm import PlayFMIE
from .plays import PlaysTVIE
from .playtvak import PlaytvakIE
from .playvid import PlayvidIE
from .playwire import PlaywireIE
@@ -530,6 +560,7 @@ from .pornhd import PornHdIE
from .pornhub import (
PornHubIE,
PornHubPlaylistIE,
PornHubUserVideosIE,
)
from .pornotube import PornotubeIE
from .pornovoisines import PornoVoisinesIE
@@ -576,6 +607,7 @@ from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
from .rtvnh import RTVNHIE
from .ruhd import RUHDIE
from .ruleporn import RulePornIE
from .rutube import (
RutubeIE,
RutubeChannelIE,
@@ -596,6 +628,7 @@ from .sbs import SBSIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE
from .screenjunkies import ScreenJunkiesIE
from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
from .senateisvp import SenateISVPIE
from .servingsys import ServingSysIE
@@ -641,7 +674,6 @@ from .southpark import (
SouthParkEsIE,
SouthParkNlIE
)
from .space import SpaceIE
from .spankbang import SpankBangIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE
@@ -709,6 +741,7 @@ from .tmz import (
TMZArticleIE,
)
from .tnaflix import (
TNAFlixNetworkEmbedIE,
TNAFlixIE,
EMPFlixIE,
MovieFapIE,
@@ -722,6 +755,7 @@ from .toutv import TouTvIE
from .toypics import ToypicsUserIE, ToypicsIE
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
from .trollvids import TrollvidsIE
from .trutube import TruTubeIE
from .tube8 import Tube8IE
from .tubitv import TubiTvIE
@@ -769,17 +803,22 @@ from .twitch import (
TwitchBookmarksIE,
TwitchStreamIE,
)
from .twitter import TwitterCardIE, TwitterIE
from .twitter import (
TwitterCardIE,
TwitterIE,
TwitterAmplifyIE,
)
from .ubu import UbuIE
from .udemy import (
UdemyIE,
UdemyCourseIE
)
from .udn import UDNEmbedIE
from .ultimedia import UltimediaIE
from .digiteka import DigitekaIE
from .unistra import UnistraIE
from .urort import UrortIE
from .ustream import UstreamIE, UstreamChannelIE
from .ustudio import UstudioIE
from .varzesh3 import Varzesh3IE
from .vbox7 import Vbox7IE
from .veehd import VeeHDIE
@@ -805,7 +844,11 @@ from .videomore import (
)
from .videopremium import VideoPremiumIE
from .videott import VideoTtIE
from .vidme import VidmeIE
from .vidme import (
VidmeIE,
VidmeUserIE,
VidmeUserLikesIE,
)
from .vidzi import VidziIE
from .vier import VierIE, VierVideosIE
from .viewster import ViewsterIE
@@ -855,6 +898,7 @@ from .webofstories import (
WebOfStoriesPlaylistIE,
)
from .weibo import WeiboIE
from .weiqitv import WeiqiTVIE
from .wimp import WimpIE
from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
@@ -915,6 +959,7 @@ from .zingmp3 import (
ZingMp3SongIE,
ZingMp3AlbumIE,
)
from .zippcast import ZippCastIE
_ALL_CLASSES = [
klass

View File

@@ -8,11 +8,7 @@ from ..compat import compat_str
from ..utils import int_or_none
class ACastBaseIE(InfoExtractor):
_API_BASE_URL = 'https://www.acast.com/api/'
class ACastIE(ACastBaseIE):
class ACastIE(InfoExtractor):
IE_NAME = 'acast'
_VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
_TEST = {
@@ -23,14 +19,19 @@ class ACastIE(ACastBaseIE):
'ext': 'mp3',
'title': '"Where Are You?": Taipei 101, Taiwan',
'timestamp': 1196172000000,
'description': 'md5:0c5d8201dfea2b93218ea986c91eee6e',
'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
'duration': 211,
}
}
def _real_extract(self, url):
channel, display_id = re.match(self._VALID_URL, url).groups()
cast_data = self._download_json(self._API_BASE_URL + 'channels/%s/acasts/%s/playback' % (channel, display_id), display_id)
embed_page = self._download_webpage(
re.sub('(?:www\.)?acast\.com', 'embedcdn.acast.com', url), display_id)
cast_data = self._parse_json(self._search_regex(
r'window\[\'acast/queries\'\]\s*=\s*([^;]+);', embed_page, 'acast data'),
display_id)['GetAcast/%s/%s' % (channel, display_id)]
return {
'id': compat_str(cast_data['id']),
@@ -44,7 +45,7 @@ class ACastIE(ACastBaseIE):
}
class ACastChannelIE(ACastBaseIE):
class ACastChannelIE(InfoExtractor):
IE_NAME = 'acast:channel'
_VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
_TEST = {
@@ -56,6 +57,7 @@ class ACastChannelIE(ACastBaseIE):
},
'playlist_mincount': 20,
}
_API_BASE_URL = 'https://www.acast.com/api/'
@classmethod
def suitable(cls, url):

View File

@@ -4,7 +4,9 @@ from .common import InfoExtractor
from ..utils import smuggle_url
class AEIE(InfoExtractor):
class AENetworksIE(InfoExtractor):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
_VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
_TESTS = [{
@@ -20,13 +22,14 @@ class AEIE(InfoExtractor):
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'expected_warnings': ['JSON-LD'],
}, {
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'info_dict': {
'id': 'eg47EERs_JsZ',
'ext': 'mp4',
'title': "Winter Is Coming",
'description': 'md5:a40e370925074260b1c8a633c632c63a',
'title': 'Winter Is Coming',
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
},
'params': {
# m3u8 download
@@ -55,4 +58,9 @@ class AEIE(InfoExtractor):
]
video_url = self._search_regex(video_url_re, webpage, 'video url')
return self.url_result(smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}))
info = self._search_json_ld(webpage, video_id, fatal=False)
info.update({
'_type': 'url_transparent',
'url': smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}),
})
return info

View File

@@ -8,6 +8,8 @@ from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
qualities,
unescapeHTML,
xpath_element,
)
@@ -31,7 +33,7 @@ class AllocineIE(InfoExtractor):
'id': '19540403',
'ext': 'mp4',
'title': 'Planes 2 Bande-annonce VF',
'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e',
'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
'thumbnail': 're:http://.*\.jpg',
},
}, {
@@ -41,7 +43,7 @@ class AllocineIE(InfoExtractor):
'id': '19544709',
'ext': 'mp4',
'title': 'Dragons 2 - Bande annonce finale VF',
'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
'description': 'md5:601d15393ac40f249648ef000720e7e3',
'thumbnail': 're:http://.*\.jpg',
},
}, {
@@ -59,14 +61,18 @@ class AllocineIE(InfoExtractor):
if typ == 'film':
video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
else:
player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player')
player_data = json.loads(player)
video_id = compat_str(player_data['refMedia'])
player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player', default=None)
if player:
player_data = json.loads(player)
video_id = compat_str(player_data['refMedia'])
else:
model = self._search_regex(r'data-model="([^"]+)">', webpage, 'data model')
model_data = self._parse_json(unescapeHTML(model), display_id)
video_id = compat_str(model_data['id'])
xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
video = xml.find('.//AcVisionVideo').attrib
video = xpath_element(xml, './/AcVisionVideo').attrib
quality = qualities(['ld', 'md', 'hd'])
formats = []

View File

@@ -0,0 +1,160 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
determine_ext,
encode_dict,
ExtractorError,
sanitized_Request,
urlencode_postdata,
)
class AnimeOnDemandIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?anime-on-demand\.de/anime/(?P<id>\d+)'
_LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in'
_APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply'
_NETRC_MACHINE = 'animeondemand'
_TEST = {
'url': 'https://www.anime-on-demand.de/anime/161',
'info_dict': {
'id': '161',
'title': 'Grimgar, Ashes and Illusions (OmU)',
'description': 'md5:6681ce3c07c7189d255ac6ab23812d31',
},
'playlist_mincount': 4,
}
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
login_form = self._form_hidden_inputs('new_user', login_page)
login_form.update({
'user[login]': username,
'user[password]': password,
})
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
request = sanitized_Request(
post_url, urlencode_postdata(encode_dict(login_form)))
request.add_header('Referer', self._LOGIN_URL)
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
error = self._search_regex(
r'<p class="alert alert-danger">(.+?)</p>',
response, 'error', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
def _real_initialize(self):
self._login()
def _real_extract(self, url):
anime_id = self._match_id(url)
webpage = self._download_webpage(url, anime_id)
if 'data-playlist=' not in webpage:
self._download_webpage(
self._APPLY_HTML5_URL, anime_id,
'Activating HTML5 beta', 'Unable to apply HTML5 beta')
webpage = self._download_webpage(url, anime_id)
csrf_token = self._html_search_meta(
'csrf-token', webpage, 'csrf token', fatal=True)
anime_title = self._html_search_regex(
r'(?s)<h1[^>]+itemprop="name"[^>]*>(.+?)</h1>',
webpage, 'anime name')
anime_description = self._html_search_regex(
r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
webpage, 'anime description', default=None)
entries = []
for episode_html in re.findall(r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage):
m = re.search(
r'class="episodebox-title"[^>]+title="Episode (?P<number>\d+) - (?P<title>.+?)"', episode_html)
if not m:
continue
episode_number = int(m.group('number'))
episode_title = m.group('title')
video_id = 'episode-%d' % episode_number
common_info = {
'id': video_id,
'series': anime_title,
'episode': episode_title,
'episode_number': episode_number,
}
formats = []
playlist_url = self._search_regex(
r'data-playlist=(["\'])(?P<url>.+?)\1',
episode_html, 'data playlist', default=None, group='url')
if playlist_url:
request = sanitized_Request(
compat_urlparse.urljoin(url, playlist_url),
headers={
'X-Requested-With': 'XMLHttpRequest',
'X-CSRF-Token': csrf_token,
'Referer': url,
'Accept': 'application/json, text/javascript, */*; q=0.01',
})
playlist = self._download_json(
request, video_id, 'Downloading playlist JSON', fatal=False)
if playlist:
playlist = playlist['playlist'][0]
title = playlist['title']
description = playlist.get('description')
for source in playlist.get('sources', []):
file_ = source.get('file')
if file_ and determine_ext(file_) == 'm3u8':
formats = self._extract_m3u8_formats(
file_, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls')
if formats:
f = common_info.copy()
f.update({
'title': title,
'description': description,
'formats': formats,
})
entries.append(f)
m = re.search(
r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
episode_html)
if m:
f = common_info.copy()
f.update({
'id': '%s-teaser' % f['id'],
'title': m.group('title'),
'url': compat_urlparse.urljoin(url, m.group('href')),
})
entries.append(f)
return self.playlist_result(entries, anime_id, anime_title, anime_description)

View File

@@ -1,11 +1,9 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .nuevo import NuevoBaseIE
class AnitubeIE(InfoExtractor):
class AnitubeIE(NuevoBaseIE):
IE_NAME = 'anitube.se'
_VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
@@ -22,38 +20,11 @@ class AnitubeIE(InfoExtractor):
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
key = self._search_regex(
r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
config_xml = self._download_xml(
'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)
video_title = config_xml.find('title').text
thumbnail = config_xml.find('image').text
duration = float(config_xml.find('duration').text)
formats = []
video_url = config_xml.find('file')
if video_url is not None:
formats.append({
'format_id': 'sd',
'url': video_url.text,
})
video_url = config_xml.find('filehd')
if video_url is not None:
formats.append({
'format_id': 'hd',
'url': video_url.text,
})
return {
'id': video_id,
'title': video_title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats
}
return self._extract_nuevo(
'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, video_id)

View File

@@ -1,24 +1,11 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class AolIE(InfoExtractor):
IE_NAME = 'on.aol.com'
_VALID_URL = r'''(?x)
(?:
aol-video:|
http://on\.aol\.com/
(?:
video/.*-|
playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
)
)
(?P<id>[0-9]+)
(?:$|\?)
'''
_VALID_URL = r'(?:aol-video:|http://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)'
_TESTS = [{
'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
@@ -29,42 +16,31 @@ class AolIE(InfoExtractor):
'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
},
'add_ie': ['FiveMin'],
}, {
'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316',
'info_dict': {
'id': '152147',
'title': 'Brace Yourself - Today\'s Weirdest News',
},
'playlist_mincount': 10,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
playlist_id = mobj.group('playlist_id')
if not playlist_id or self._downloader.params.get('noplaylist'):
return self.url_result('5min:%s' % video_id)
video_id = self._match_id(url)
return self.url_result('5min:%s' % video_id)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
playlist_html = self._search_regex(
r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
'playlist HTML')
entries = [{
'_type': 'url',
'url': 'aol-video:%s' % m.group('id'),
'ie_key': 'Aol',
} for m in re.finditer(
r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
playlist_html)]
class AolFeaturesIE(InfoExtractor):
IE_NAME = 'features.aol.com'
_VALID_URL = r'http://features\.aol\.com/video/(?P<id>[^/?#]+)'
return {
'_type': 'playlist',
'id': playlist_id,
'display_id': mobj.group('playlist_display_id'),
'title': title,
'entries': entries,
}
_TESTS = [{
'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
'md5': '7db483bb0c09c85e241f84a34238cc75',
'info_dict': {
'id': '519507715',
'ext': 'mp4',
'title': 'What To Watch - February 17, 2016',
},
'add_ie': ['FiveMin'],
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
return self.url_result(self._search_regex(
r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"',
webpage, '5min embed url'), 'FiveMin')

View File

@@ -12,7 +12,7 @@ from ..utils import (
class AppleTrailersIE(InfoExtractor):
IE_NAME = 'appletrailers'
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_VALID_URL = r'https?://(?:www\.|movie)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TESTS = [{
'url': 'http://trailers.apple.com/trailers/wb/manofsteel/',
'info_dict': {
@@ -73,6 +73,9 @@ class AppleTrailersIE(InfoExtractor):
}, {
'url': 'http://trailers.apple.com/ca/metropole/autrui/',
'only_matching': True,
}, {
'url': 'http://movietrailers.apple.com/trailers/focus_features/kuboandthetwostrings/',
'only_matching': True,
}]
_JSON_RE = r'iTunes.playURL\((.*?)\);'

View File

@@ -13,6 +13,7 @@ from ..utils import (
unified_strdate,
get_element_by_attribute,
int_or_none,
NO_DEFAULT,
qualities,
)
@@ -22,7 +23,7 @@ from ..utils import (
class ArteTvIE(InfoExtractor):
_VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html'
_VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
IE_NAME = 'arte.tv'
def _real_extract(self, url):
@@ -62,7 +63,7 @@ class ArteTvIE(InfoExtractor):
class ArteTVPlus7IE(InfoExtractor):
IE_NAME = 'arte.tv:+7'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&+])'
@classmethod
def _extract_url_info(cls, url):
@@ -93,12 +94,40 @@ class ArteTVPlus7IE(InfoExtractor):
json_url = self._html_search_regex(
patterns, webpage, 'json vp url', default=None)
if not json_url:
iframe_url = self._html_search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
webpage, 'iframe url', group='url')
json_url = compat_parse_qs(
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
return self._extract_from_json_url(json_url, video_id, lang)
def find_iframe_url(webpage, default=NO_DEFAULT):
return self._html_search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
webpage, 'iframe url', group='url', default=default)
iframe_url = find_iframe_url(webpage, None)
if not iframe_url:
embed_url = self._html_search_regex(
r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
if embed_url:
player = self._download_json(
embed_url, video_id, 'Downloading player page')
iframe_url = find_iframe_url(player['html'])
# en and es URLs produce react-based pages with different layout (e.g.
# http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
if not iframe_url:
program = self._search_regex(
r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
webpage, 'program', default=None)
if program:
embed_html = self._parse_json(program, video_id)
if embed_html:
iframe_url = find_iframe_url(embed_html['embed_html'])
if iframe_url:
json_url = compat_parse_qs(
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
if json_url:
return self._extract_from_json_url(json_url, video_id, lang)
# Differend kind of embed URL (e.g.
# http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
embed_url = self._search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1',
webpage, 'embed url', group='url')
return self.url_result(embed_url)
def _extract_from_json_url(self, json_url, video_id, lang):
info = self._download_json(json_url, video_id)
@@ -106,7 +135,7 @@ class ArteTVPlus7IE(InfoExtractor):
upload_date_str = player_info.get('shootingDate')
if not upload_date_str:
upload_date_str = player_info.get('VDA', '').split(' ')[0]
upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]
title = player_info['VTI'].strip()
subtitle = player_info.get('VSU', '').strip()
@@ -122,27 +151,30 @@ class ArteTVPlus7IE(InfoExtractor):
}
qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ'])
LANGS = {
'fr': 'F',
'de': 'A',
'en': 'E[ANG]',
'es': 'E[ESP]',
}
formats = []
for format_id, format_dict in player_info['VSR'].items():
f = dict(format_dict)
versionCode = f.get('versionCode')
langcode = {
'fr': 'F',
'de': 'A',
}.get(lang, lang)
lang_rexs = [r'VO?%s' % langcode, r'VO?.-ST%s' % langcode]
lang_pref = (
None if versionCode is None else (
10 if any(re.match(r, versionCode) for r in lang_rexs)
else -10))
langcode = LANGS.get(lang, lang)
lang_rexs = [r'VO?%s-' % re.escape(langcode), r'VO?.-ST%s$' % re.escape(langcode)]
lang_pref = None
if versionCode:
matched_lang_rexs = [r for r in lang_rexs if re.match(r, versionCode)]
lang_pref = -10 if not matched_lang_rexs else 10 * len(matched_lang_rexs)
source_pref = 0
if versionCode is not None:
# The original version with subtitles has lower relevance
if re.match(r'VO-ST(F|A)', versionCode):
if re.match(r'VO-ST(F|A|E)', versionCode):
source_pref -= 10
# The version with sourds/mal subtitles has also lower relevance
elif re.match(r'VO?(F|A)-STM\1', versionCode):
elif re.match(r'VO?(F|A|E)-STM\1', versionCode):
source_pref -= 9
format = {
'format_id': format_id,
@@ -175,7 +207,7 @@ class ArteTVPlus7IE(InfoExtractor):
# It also uses the arte_vp_url url from the webpage to extract the information
class ArteTVCreativeIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:creative'
_VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de)/(?:magazine?/)?(?P<id>[^?#]+)'
_VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:magazine?/)?(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
@@ -199,30 +231,25 @@ class ArteTVCreativeIE(ArteTVPlus7IE):
class ArteTVFutureIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:future'
_VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de)/(thema|sujet)/.*?#article-anchor-(?P<id>\d+)'
_VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
_TESTS = [{
'url': 'http://future.arte.tv/fr/info-sciences/les-ecrevisses-aussi-sont-anxieuses',
'info_dict': {
'id': '5201',
'id': '050940-028-A',
'ext': 'mp4',
'title': 'Les champignons au secours de la planète',
'upload_date': '20131101',
'title': 'Les écrevisses aussi peuvent être anxieuses',
'upload_date': '20140902',
},
}
def _real_extract(self, url):
anchor_id, lang = self._extract_url_info(url)
webpage = self._download_webpage(url, anchor_id)
row = self._search_regex(
r'(?s)id="%s"[^>]*>.+?(<div[^>]*arte_vp_url[^>]*>)' % anchor_id,
webpage, 'row')
return self._extract_from_webpage(row, anchor_id, lang)
}, {
'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable',
'only_matching': True,
}]
class ArteTVDDCIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:ddc'
_VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
_VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)'
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
@@ -240,7 +267,7 @@ class ArteTVDDCIE(ArteTVPlus7IE):
class ArteTVConcertIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:concert'
_VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>de|fr)/(?P<id>.+)'
_VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
@@ -255,6 +282,54 @@ class ArteTVConcertIE(ArteTVPlus7IE):
}
class ArteTVCinemaIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:cinema'
_VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
_TEST = {
'url': 'http://cinema.arte.tv/de/node/38291',
'md5': '6b275511a5107c60bacbeeda368c3aa1',
'info_dict': {
'id': '055876-000_PWA12025-D',
'ext': 'mp4',
'title': 'Tod auf dem Nil',
'upload_date': '20160122',
'description': 'md5:7f749bbb77d800ef2be11d54529b96bc',
},
}
class ArteTVMagazineIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:magazine'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/magazine/[^/]+/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
# Embedded via <iframe src="http://www.arte.tv/arte_vp/index.php?json_url=..."
'url': 'http://www.arte.tv/magazine/trepalium/fr/entretien-avec-le-realisateur-vincent-lannoo-trepalium',
'md5': '2a9369bcccf847d1c741e51416299f25',
'info_dict': {
'id': '065965-000-A',
'ext': 'mp4',
'title': 'Trepalium - Extrait Ep.01',
'upload_date': '20160121',
},
}, {
# Embedded via <iframe src="http://www.arte.tv/guide/fr/embed/054813-004-A/medium"
'url': 'http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium',
'md5': 'fedc64fc7a946110fe311634e79782ca',
'info_dict': {
'id': '054813-004_PLUS7-F',
'ext': 'mp4',
'title': 'Trepalium (4/6)',
'description': 'md5:10057003c34d54e95350be4f9b05cb40',
'upload_date': '20160218',
},
}, {
'url': 'http://www.arte.tv/magazine/metropolis/de/frank-woeste-german-paris-metropolis',
'only_matching': True,
}]
class ArteTVEmbedIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:embed'
_VALID_URL = r'''(?x)

View File

@@ -132,11 +132,6 @@ class AtresPlayerIE(InfoExtractor):
})
formats.append(format_info)
m3u8_url = player.get('urlVideoHls')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, episode_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
timestamp = int_or_none(self._download_webpage(
self._TIME_API_URL,
video_id, 'Downloading timestamp', fatal=False), 1000, time.time())

View File

@@ -10,9 +10,9 @@ from ..utils import (
class AudiMediaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?P<id>[^/?#]+)'
_TEST = {
'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test',
'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467',
'md5': '79a8b71c46d49042609795ab59779b66',
'info_dict': {
'id': '1565',
@@ -32,7 +32,10 @@ class AudiMediaIE(InfoExtractor):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload')
raw_payload = self._search_regex([
r'class="amtv-embed"[^>]+id="([^"]+)"',
r'class=\\"amtv-embed\\"[^>]+id=\\"([^"]+)\\"',
], webpage, 'raw payload')
_, stage_mode, video_id, lang = raw_payload.split('-')
# TODO: handle s and e stage_mode (live streams and ended live streams)
@@ -59,13 +62,19 @@ class AudiMediaIE(InfoExtractor):
video_version_url = video_version.get('download_url') or video_version.get('stream_url')
if not video_version_url:
continue
formats.append({
f = {
'url': video_version_url,
'width': int_or_none(video_version.get('width')),
'height': int_or_none(video_version.get('height')),
'abr': int_or_none(video_version.get('audio_bitrate')),
'vbr': int_or_none(video_version.get('video_bitrate')),
})
}
bitrate = self._search_regex(r'(\d+)k', video_version_url, 'bitrate', default=None)
if bitrate:
f.update({
'format_id': 'http-%s' % bitrate,
})
formats.append(f)
self._sort_formats(formats)
return {

View File

@@ -3,7 +3,11 @@ from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import float_or_none
from ..utils import (
ExtractorError,
float_or_none,
sanitized_Request,
)
class AzubuIE(InfoExtractor):
@@ -91,3 +95,37 @@ class AzubuIE(InfoExtractor):
'view_count': view_count,
'formats': formats,
}
class AzubuLiveIE(InfoExtractor):
_VALID_URL = r'http://www.azubu.tv/(?P<id>[^/]+)$'
_TEST = {
'url': 'http://www.azubu.tv/MarsTVMDLen',
'only_matching': True,
}
def _real_extract(self, url):
user = self._match_id(url)
info = self._download_json(
'http://api.azubu.tv/public/modules/last-video/{0}/info'.format(user),
user)['data']
if info['type'] != 'STREAM':
raise ExtractorError('{0} is not streaming live'.format(user), expected=True)
req = sanitized_Request(
'https://edge-elb.api.brightcove.com/playback/v1/accounts/3361910549001/videos/ref:' + info['reference_id'])
req.add_header('Accept', 'application/json;pk=BCpkADawqM1gvI0oGWg8dxQHlgT8HkdE2LnAlWAZkOlznO39bSZX726u4JqnDsK3MDXcO01JxXK2tZtJbgQChxgaFzEVdHRjaDoxaOu8hHOO8NYhwdxw9BzvgkvLUlpbDNUuDoc4E4wxDToV')
bc_info = self._download_json(req, user)
m3u8_url = next(source['src'] for source in bc_info['sources'] if source['container'] == 'M2TS')
formats = self._extract_m3u8_formats(m3u8_url, user, ext='mp4')
return {
'id': info['id'],
'title': self._live_title(info['title']),
'uploader_id': user,
'formats': formats,
'is_live': True,
'thumbnail': bc_info['poster'],
}

View File

@@ -86,7 +86,7 @@ class BBCCoUkIE(InfoExtractor):
'id': 'b00yng1d',
'ext': 'flv',
'title': 'The Voice UK: Series 3: Blind Auditions 5',
'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
'description': 'Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.',
'duration': 5100,
},
'params': {
@@ -193,6 +193,19 @@ class BBCCoUkIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
}, {
# compact player (https://github.com/rg3/youtube-dl/issues/8147)
'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
'info_dict': {
'id': 'p028bfkj',
'ext': 'flv',
'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
'only_matching': True,
@@ -482,9 +495,11 @@ class BBCCoUkIE(InfoExtractor):
if programme_id:
formats, subtitles = self._download_media_selector(programme_id)
title = self._og_search_title(webpage, default=None) or self._html_search_regex(
r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>', webpage, 'title')
(r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>',
r'<div[^>]+class="info"[^>]*>\s*<h1>(.+?)</h1>'), webpage, 'title')
description = self._search_regex(
r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
(r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
r'<div[^>]+class="info_+synopsis"[^>]*>([^<]+)</div>'),
webpage, 'description', default=None)
if not description:
description = self._html_search_meta('description', webpage)
@@ -718,19 +733,10 @@ class BBCIE(BBCCoUkIE):
webpage = self._download_webpage(url, playlist_id)
timestamp = None
playlist_title = None
playlist_description = None
ld = self._parse_json(
self._search_regex(
r'(?s)<script type="application/ld\+json">(.+?)</script>',
webpage, 'ld json', default='{}'),
playlist_id, fatal=False)
if ld:
timestamp = parse_iso8601(ld.get('datePublished'))
playlist_title = ld.get('headline')
playlist_description = ld.get('articleBody')
json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
timestamp = json_ld_info.get('timestamp')
playlist_title = json_ld_info.get('title')
playlist_description = json_ld_info.get('description')
if not timestamp:
timestamp = parse_iso8601(self._search_regex(

View File

@@ -28,10 +28,10 @@ class BleacherReportIE(InfoExtractor):
'add_ie': ['Ooyala'],
}, {
'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo',
'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50',
'md5': '6a5cd403418c7b01719248ca97fb0692',
'info_dict': {
'id': '2586817',
'ext': 'mp4',
'ext': 'webm',
'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo',
'timestamp': 1446839961,
'uploader': 'Sean Fay',
@@ -93,10 +93,14 @@ class BleacherReportCMSIE(AMPIE):
'md5': '8c2c12e3af7805152675446c905d159b',
'info_dict': {
'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
'ext': 'flv',
'ext': 'mp4',
'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
},
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):

View File

@@ -0,0 +1,60 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_parse_qs
from ..utils import ExtractorError
class BokeCCBaseIE(InfoExtractor):
def _extract_bokecc_formats(self, webpage, video_id, format_id=None):
player_params_str = self._html_search_regex(
r'<(?:script|embed)[^>]+src="http://p\.bokecc\.com/player\?([^"]+)',
webpage, 'player params')
player_params = compat_parse_qs(player_params_str)
info_xml = self._download_xml(
'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % (
player_params['siteid'][0], player_params['vid'][0]), video_id)
formats = [{
'format_id': format_id,
'url': quality.find('./copy').attrib['playurl'],
'preference': int(quality.attrib['value']),
} for quality in info_xml.findall('./video/quality')]
self._sort_formats(formats)
return formats
class BokeCCIE(BokeCCBaseIE):
_IE_DESC = 'CC视频'
_VALID_URL = r'http://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
_TESTS = [{
'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B',
'info_dict': {
'id': 'CD0C5D3C8614B28B_E44D40C15E65EA30',
'ext': 'flv',
'title': 'BokeCC Video',
},
}]
def _real_extract(self, url):
qs = compat_parse_qs(re.match(self._VALID_URL, url).group('query'))
if not qs.get('vid') or not qs.get('uid'):
raise ExtractorError('Invalid URL', expected=True)
video_id = '%s_%s' % (qs['uid'][0], qs['vid'][0])
webpage = self._download_webpage(url, video_id)
return {
'id': video_id,
'title': 'BokeCC Video', # no title provided in the webpage
'formats': self._extract_bokecc_formats(webpage, video_id),
}

View File

@@ -1,7 +1,13 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
js_to_json,
determine_ext,
)
class BpbIE(InfoExtractor):
@@ -10,7 +16,8 @@ class BpbIE(InfoExtractor):
_TEST = {
'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
'md5': '0792086e8e2bfbac9cdf27835d5f2093',
# md5 fails in Python 2.6 due to buggy server response and wrong handling of urllib2
'md5': 'c4f84c8a8044ca9ff68bb8441d300b3f',
'info_dict': {
'id': '297',
'ext': 'mp4',
@@ -25,13 +32,26 @@ class BpbIE(InfoExtractor):
title = self._html_search_regex(
r'<h2 class="white">(.*?)</h2>', webpage, 'title')
video_url = self._html_search_regex(
r'(http://film\.bpb\.de/player/dokument_[0-9]+\.mp4)',
webpage, 'video URL')
video_info_dicts = re.findall(
r"({\s*src:\s*'http://film\.bpb\.de/[^}]+})", webpage)
formats = []
for video_info in video_info_dicts:
video_info = self._parse_json(video_info, video_id, transform_source=js_to_json)
quality = video_info['quality']
video_url = video_info['src']
formats.append({
'url': video_url,
'preference': 10 if quality == 'high' else 0,
'format_note': quality,
'format_id': '%s-%s' % (quality, determine_ext(video_url)),
})
self._sort_formats(formats)
return {
'id': video_id,
'url': video_url,
'formats': formats,
'title': title,
'description': self._og_search_description(webpage),
}

View File

@@ -4,12 +4,13 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import js_to_json
class C56IE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
IE_NAME = '56.com'
_TEST = {
_TESTS = [{
'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
'md5': 'e59995ac63d0457783ea05f93f12a866',
'info_dict': {
@@ -18,12 +19,29 @@ class C56IE(InfoExtractor):
'title': '网事知多少 第32期车怒',
'duration': 283.813,
},
}
}, {
'url': 'http://www.56.com/u47/v_MTM5NjQ5ODc2.html',
'md5': '',
'info_dict': {
'id': '82247482',
'title': '爱的诅咒之杜鹃花开',
},
'playlist_count': 7,
'add_ie': ['Sohu'],
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
text_id = mobj.group('textid')
webpage = self._download_webpage(url, text_id)
sohu_video_info_str = self._search_regex(
r'var\s+sohuVideoInfo\s*=\s*({[^}]+});', webpage, 'Sohu video info', default=None)
if sohu_video_info_str:
sohu_video_info = self._parse_json(
sohu_video_info_str, text_id, transform_source=js_to_json)
return self.url_result(sohu_video_info['url'], 'Sohu')
page = self._download_json(
'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')

View File

@@ -6,7 +6,7 @@ from ..utils import float_or_none
class CanvasIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = {
_TESTS = [{
'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
'md5': 'ea838375a547ac787d4064d8c7860a6c',
'info_dict': {
@@ -18,7 +18,27 @@ class CanvasIE(InfoExtractor):
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 49.02,
}
}
}, {
# with subtitles
'url': 'http://www.canvas.be/video/panorama/2016/pieter-0167',
'info_dict': {
'id': 'mz-ast-5240ff21-2d30-4101-bba6-92b5ec67c625',
'display_id': 'pieter-0167',
'ext': 'mp4',
'title': 'Pieter 0167',
'description': 'md5:943cd30f48a5d29ba02c3a104dc4ec4e',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 2553.08,
'subtitles': {
'nl': [{
'ext': 'vtt',
}],
},
},
'params': {
'skip_download': True,
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
@@ -54,6 +74,14 @@ class CanvasIE(InfoExtractor):
})
self._sort_formats(formats)
subtitles = {}
subtitle_urls = data.get('subtitleUrls')
if isinstance(subtitle_urls, list):
for subtitle in subtitle_urls:
subtitle_url = subtitle.get('url')
if subtitle_url and subtitle.get('type') == 'CLOSED':
subtitles.setdefault('nl', []).append({'url': subtitle_url})
return {
'id': video_id,
'display_id': display_id,
@@ -62,4 +90,5 @@ class CanvasIE(InfoExtractor):
'formats': formats,
'duration': float_or_none(data.get('duration'), 1000),
'thumbnail': data.get('posterImageUrl'),
'subtitles': subtitles,
}

113
youtube_dl/extractor/cbc.py Normal file
View File

@@ -0,0 +1,113 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import js_to_json
class CBCIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
# with mediaId
'url': 'http://www.cbc.ca/22minutes/videos/clips-season-23/don-cherry-play-offs',
'info_dict': {
'id': '2682904050',
'ext': 'flv',
'title': 'Don Cherry All-Stars',
'description': 'Don Cherry has a bee in his bonnet about AHL player John Scott because that guys got heart.',
'timestamp': 1454475540,
'upload_date': '20160203',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
# with clipId
'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live',
'info_dict': {
'id': '2487345465',
'ext': 'flv',
'title': 'Robin Williams freestyles on 90 Minutes Live',
'description': 'Wacky American comedian Robin Williams shows off his infamous "freestyle" comedic talents while being interviewed on CBC\'s 90 Minutes Live.',
'upload_date': '19700101',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
# multiple iframes
'url': 'http://www.cbc.ca/natureofthings/blog/birds-eye-view-from-vancouvers-burrard-street-bridge-how-we-got-the-shot',
'playlist': [{
'info_dict': {
'id': '2680832926',
'ext': 'flv',
'title': 'An Eagle\'s-Eye View Off Burrard Bridge',
'description': 'Hercules the eagle flies from Vancouver\'s Burrard Bridge down to a nearby park with a mini-camera strapped to his back.',
'upload_date': '19700101',
},
}, {
'info_dict': {
'id': '2658915080',
'ext': 'flv',
'title': 'Fly like an eagle!',
'description': 'Eagle equipped with a mini camera flies from the world\'s tallest tower',
'upload_date': '19700101',
},
}],
'params': {
# rtmp download
'skip_download': True,
},
}]
@classmethod
def suitable(cls, url):
return False if CBCPlayerIE.suitable(url) else super(CBCIE, cls).suitable(url)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_init = self._search_regex(
r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage, 'player init',
default=None)
if player_init:
player_info = self._parse_json(player_init, display_id, js_to_json)
media_id = player_info.get('mediaId')
if not media_id:
clip_id = player_info['clipId']
media_id = self._download_json(
'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
clip_id)['entries'][0]['id'].split('/')[-1]
return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
else:
entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]
return self.playlist_result(entries)
class CBCPlayerIE(InfoExtractor):
_VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)'
_TEST = {
'url': 'http://www.cbc.ca/player/play/2683190193',
'info_dict': {
'id': '2683190193',
'ext': 'flv',
'title': 'Gerry Runs a Sweat Shop',
'description': 'md5:b457e1c01e8ff408d9d801c1c2cd29b0',
'timestamp': 1455067800,
'upload_date': '20160210',
},
'params': {
# rtmp download
'skip_download': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result(
'http://feed.theplatform.com/f/ExhSPC/vms_5akSXx4Ng_Zn?byGuid=%s' % video_id,
'ThePlatformFeed', video_id)

View File

@@ -1,16 +1,17 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import remove_start
from .theplatform import ThePlatformIE
from ..utils import (
parse_duration,
find_xpath_attr,
)
class CBSNewsIE(InfoExtractor):
class CBSNewsIE(ThePlatformIE):
IE_DESC = 'CBS News'
_VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?P<id>[\da-z_-]+)'
_VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
_TESTS = [
{
@@ -31,59 +32,57 @@ class CBSNewsIE(InfoExtractor):
'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
'info_dict': {
'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
'ext': 'flv',
'ext': 'mp4',
'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 205,
'subtitles': {
'en': [{
'ext': 'ttml',
}],
},
},
'params': {
# rtmp download
# m3u8 download
'skip_download': True,
},
},
]
def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
return {
'en': [{
'ext': 'ttml',
'url': closed_caption_e.attrib['value'],
}]
} if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_info = json.loads(self._html_search_regex(
video_info = self._parse_json(self._html_search_regex(
r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
webpage, 'video JSON info'))
webpage, 'video JSON info'), video_id)
item = video_info['item'] if 'item' in video_info else video_info
title = item.get('articleTitle') or item.get('hed')
duration = item.get('duration')
thumbnail = item.get('mediaImage') or item.get('thumbnail')
subtitles = {}
formats = []
for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
uri = item.get('media' + format_id + 'URI')
if not uri:
pid = item.get('media' + format_id)
if not pid:
continue
uri = remove_start(uri, '{manifest:none}')
fmt = {
'url': uri,
'format_id': format_id,
}
if uri.startswith('rtmp'):
play_path = re.sub(
r'{slistFilePath}', '',
uri.split('<break>')[-1].split('{break}')[-1])
play_path = re.sub(
r'{manifest:.+}.*$', '', play_path)
fmt.update({
'app': 'ondemand?auth=cbs',
'play_path': 'mp4:' + play_path,
'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
'page_url': 'http://www.cbsnews.com',
'ext': 'flv',
})
elif uri.endswith('.m3u8'):
fmt['ext'] = 'mp4'
formats.append(fmt)
release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?format=SMIL&mbr=true' % pid
tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid)
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
self._sort_formats(formats)
return {
'id': video_id,
@@ -91,4 +90,43 @@ class CBSNewsIE(InfoExtractor):
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}
class CBSNewsLiveVideoIE(InfoExtractor):
IE_DESC = 'CBS News Live Videos'
_VALID_URL = r'http://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
_TEST = {
'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
'info_dict': {
'id': 'clinton-sanders-prepare-to-face-off-in-nh',
'ext': 'flv',
'title': 'Clinton, Sanders Prepare To Face Off In NH',
'duration': 334,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_info = self._parse_json(self._html_search_regex(
r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
hdcore_sign = 'hdcore=3.3.1'
f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
if f4m_formats:
for entry in f4m_formats:
# URLs without the extra param induce an 404 error
entry.update({'extra_param_to_segment_url': hdcore_sign})
return {
'id': video_id,
'title': video_info['headline'],
'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
'duration': parse_duration(video_info.get('segmentDur')),
'formats': f4m_formats,
}

View File

@@ -45,7 +45,7 @@ class CCCIE(InfoExtractor):
title = self._html_search_regex(
r'(?s)<h1>(.*?)</h1>', webpage, 'title')
description = self._html_search_regex(
r"(?s)<h3>About</h3>(.+?)<h3>",
r'(?s)<h3>About</h3>(.+?)<h3>',
webpage, 'description', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
r"(?s)<span[^>]+class='[^']*fa-calendar-o'[^>]*>(.+?)</span>",

View File

@@ -177,16 +177,16 @@ class CeskaTelevizeIE(InfoExtractor):
for divider in [1000, 60, 60, 100]:
components.append(msec % divider)
msec //= divider
return "{3:02}:{2:02}:{1:02},{0:03}".format(*components)
return '{3:02}:{2:02}:{1:02},{0:03}'.format(*components)
def _fix_subtitle(subtitle):
for line in subtitle.splitlines():
m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line)
m = re.match(r'^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$', line)
if m:
yield m.group(1)
start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
yield "{0} --> {1}".format(start, stop)
yield '{0} --> {1}'.format(start, stop)
else:
yield line
return "\r\n".join(_fix_subtitle(subtitles))
return '\r\n'.join(_fix_subtitle(subtitles))

View File

@@ -21,6 +21,10 @@ class CinemassacreIE(InfoExtractor):
'title': '“Angry Video Game Nerd: The Movie” Trailer',
'description': 'md5:fb87405fcb42a331742a0dce2708560b',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
@@ -31,14 +35,18 @@ class CinemassacreIE(InfoExtractor):
'upload_date': '20131002',
'title': 'The Mummys Hand (1940)',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
# Youtube embedded video
'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
'md5': 'df4cf8a1dcedaec79a73d96d83b99023',
'md5': 'ec9838a5520ef5409b3e4e42fcb0a3b9',
'info_dict': {
'id': 'OEVzPCY2T-g',
'ext': 'mp4',
'ext': 'webm',
'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
'upload_date': '20061207',
'uploader': 'Cinemassacre',
@@ -49,12 +57,12 @@ class CinemassacreIE(InfoExtractor):
{
# Youtube embedded video
'url': 'http://cinemassacre.com/2006/09/01/mckids/',
'md5': '6eb30961fa795fedc750eac4881ad2e1',
'md5': '7393c4e0f54602ad110c793eb7a6513a',
'info_dict': {
'id': 'FnxsNhuikpo',
'ext': 'mp4',
'ext': 'webm',
'upload_date': '20060901',
'uploader': 'Cinemassacre Extras',
'uploader': 'Cinemassacre Extra',
'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53',
'uploader_id': 'Cinemassacre',
'title': 'AVGN: McKids',
@@ -69,7 +77,11 @@ class CinemassacreIE(InfoExtractor):
'description': 'Lets Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!',
'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays',
'upload_date': '20150525',
}
},
'params': {
# m3u8 download
'skip_download': True,
},
}
]

View File

@@ -51,9 +51,7 @@ class CNETIE(ThePlatformIE):
uploader = None
uploader_id = None
mpx_account = data['config']['uvpConfig']['default']['mpx_account']
metadata = self.get_metadata('%s/%s' % (mpx_account, list(vdata['files'].values())[0]), video_id)
metadata = self.get_metadata('kYEXFC/%s' % list(vdata['files'].values())[0], video_id)
description = vdata.get('description') or metadata.get('description')
duration = int_or_none(vdata.get('duration')) or metadata.get('duration')
@@ -62,7 +60,7 @@ class CNETIE(ThePlatformIE):
for (fkey, vid) in vdata['files'].items():
if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']:
continue
release_url = 'http://link.theplatform.com/s/%s/%s?format=SMIL&mbr=true' % (mpx_account, vid)
release_url = 'http://link.theplatform.com/s/kYEXFC/%s?format=SMIL&mbr=true' % vid
if fkey == 'hds':
release_url += '&manifest=f4m'
tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey)

View File

@@ -26,14 +26,14 @@ class CNNIE(InfoExtractor):
'upload_date': '20130609',
},
}, {
"url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
"md5": "b5cc60c60a3477d185af8f19a2a26f4e",
"info_dict": {
'url': 'http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29',
'md5': 'b5cc60c60a3477d185af8f19a2a26f4e',
'info_dict': {
'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology',
'ext': 'mp4',
"title": "Student's epic speech stuns new freshmen",
"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
"upload_date": "20130821",
'title': "Student's epic speech stuns new freshmen",
'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
'upload_date': '20130821',
}
}, {
'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',

View File

@@ -46,9 +46,9 @@ class CollegeRamaIE(InfoExtractor):
video_id = self._match_id(url)
player_options_request = {
"getPlayerOptionsRequest": {
"ResourceId": video_id,
"QueryString": "",
'getPlayerOptionsRequest': {
'ResourceId': video_id,
'QueryString': '',
}
}

View File

@@ -2,6 +2,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
parse_duration,
@@ -14,14 +15,13 @@ class ComCarCoffIE(InfoExtractor):
_TESTS = [{
'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
'info_dict': {
'id': 'miranda-sings-happy-thanksgiving-miranda',
'id': '2494164',
'ext': 'mp4',
'upload_date': '20141127',
'timestamp': 1417107600,
'duration': 1232,
'title': 'Happy Thanksgiving Miranda',
'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg',
},
'params': {
'skip_download': 'requires ffmpeg',
@@ -39,15 +39,14 @@ class ComCarCoffIE(InfoExtractor):
r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'),
display_id)['videoData']
video_id = full_data['activeVideo']['video']
video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id]
display_id = full_data['activeVideo']['video']
video_data = full_data.get('videos', {}).get(display_id) or full_data['singleshots'][display_id]
video_id = compat_str(video_data['mediaId'])
thumbnails = [{
'url': video_data['images']['thumb'],
}, {
'url': video_data['images']['poster'],
}]
formats = self._extract_m3u8_formats(
video_data['mediaUrl'], video_id, ext='mp4')
timestamp = int_or_none(video_data.get('pubDateTime')) or parse_iso8601(
video_data.get('pubDate'))
@@ -55,6 +54,8 @@ class ComCarCoffIE(InfoExtractor):
video_data.get('duration'))
return {
'_type': 'url_transparent',
'url': 'crackle:%s' % video_id,
'id': video_id,
'display_id': display_id,
'title': video_data['title'],
@@ -62,6 +63,7 @@ class ComCarCoffIE(InfoExtractor):
'timestamp': timestamp,
'duration': duration,
'thumbnails': thumbnails,
'formats': formats,
'season_number': int_or_none(video_data.get('season')),
'episode_number': int_or_none(video_data.get('episode')),
'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),
}

View File

@@ -16,11 +16,11 @@ from ..utils import (
class ComedyCentralIE(MTVServicesInfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
(video-clips|episodes|cc-studios|video-collections|full-episodes)
(video-clips|episodes|cc-studios|video-collections|full-episodes|shows)
/(?P<title>.*)'''
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
_TEST = {
_TESTS = [{
'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
'info_dict': {
@@ -29,7 +29,10 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
'description': 'After a certain point, breastfeeding becomes c**kblocking.',
},
}
}, {
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
'only_matching': True,
}]
class ComedyCentralShowsIE(MTVServicesInfoExtractor):
@@ -192,7 +195,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
if len(altMovieParams) == 0:
raise ExtractorError('unable to find Flash URL in webpage ' + url)
else:
mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
mMovieParams = [('http://media.mtvnservices.com/' + altMovieParams[0], altMovieParams[0])]
uri = mMovieParams[0][1]
# Correct cc.com in uri

View File

@@ -10,17 +10,19 @@ import re
import socket
import sys
import time
import math
from ..compat import (
compat_cookiejar,
compat_cookies,
compat_etree_fromstring,
compat_getpass,
compat_http_client,
compat_os_name,
compat_str,
compat_urllib_error,
compat_urllib_parse,
compat_urlparse,
compat_str,
compat_etree_fromstring,
)
from ..utils import (
NO_DEFAULT,
@@ -34,6 +36,7 @@ from ..utils import (
fix_xml_ampersands,
float_or_none,
int_or_none,
parse_iso8601,
RegexNotFoundError,
sanitize_filename,
sanitized_Request,
@@ -43,6 +46,8 @@ from ..utils import (
xpath_text,
xpath_with_ns,
determine_protocol,
parse_duration,
mimetype2ext,
)
@@ -153,12 +158,14 @@ class InfoExtractor(object):
thumbnail: Full URL to a video thumbnail image.
description: Full video description.
uploader: Full name of the video uploader.
license: License name the video is licensed under.
creator: The main artist who created the video.
release_date: The date (YYYYMMDD) when the video was released.
timestamp: UNIX timestamp of the moment the video became available.
upload_date: Video upload date (YYYYMMDD).
If not explicitly set, calculated from timestamp.
uploader_id: Nickname or id of the video uploader.
uploader_url: Full URL to a personal webpage of the video uploader.
location: Physical location where the video was filmed.
subtitles: The available subtitles as a dictionary in the format
{language: subformats}. "subformats" is a list sorted from
@@ -421,7 +428,7 @@ class InfoExtractor(object):
self.to_screen('Saving request to ' + filename)
# Working around MAX_PATH limitation on Windows (see
# http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
if os.name == 'nt':
if compat_os_name == 'nt':
absfilepath = os.path.abspath(filename)
if len(absfilepath) > 259:
filename = '\\\\?\\' + absfilepath
@@ -590,7 +597,7 @@ class InfoExtractor(object):
if mobj:
break
if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty():
if not self._downloader.params.get('no_color') and compat_os_name != 'nt' and sys.stderr.isatty():
_name = '\033[0;34m%s\033[0m' % name
else:
_name = name
@@ -633,7 +640,7 @@ class InfoExtractor(object):
downloader_params = self._downloader.params
# Attempt to use provided username and password or .netrc data
if downloader_params.get('username', None) is not None:
if downloader_params.get('username') is not None:
username = downloader_params['username']
password = downloader_params['password']
elif downloader_params.get('usenetrc', False):
@@ -660,7 +667,7 @@ class InfoExtractor(object):
return None
downloader_params = self._downloader.params
if downloader_params.get('twofactor', None) is not None:
if downloader_params.get('twofactor') is not None:
return downloader_params['twofactor']
return compat_getpass('Type %s and press [Return]: ' % note)
@@ -741,7 +748,7 @@ class InfoExtractor(object):
'mature': 17,
'restricted': 19,
}
return RATING_TABLE.get(rating.lower(), None)
return RATING_TABLE.get(rating.lower())
def _family_friendly_search(self, html):
# See http://schema.org/VideoObject
@@ -756,12 +763,48 @@ class InfoExtractor(object):
'0': 18,
'false': 18,
}
return RATING_TABLE.get(family_friendly.lower(), None)
return RATING_TABLE.get(family_friendly.lower())
def _twitter_search_player(self, html):
return self._html_search_meta('twitter:player', html,
'twitter card player')
def _search_json_ld(self, html, video_id, **kwargs):
json_ld = self._search_regex(
r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
html, 'JSON-LD', group='json_ld', **kwargs)
if not json_ld:
return {}
return self._json_ld(json_ld, video_id, fatal=kwargs.get('fatal', True))
def _json_ld(self, json_ld, video_id, fatal=True):
if isinstance(json_ld, compat_str):
json_ld = self._parse_json(json_ld, video_id, fatal=fatal)
if not json_ld:
return {}
info = {}
if json_ld.get('@context') == 'http://schema.org':
item_type = json_ld.get('@type')
if item_type == 'TVEpisode':
info.update({
'episode': unescapeHTML(json_ld.get('name')),
'episode_number': int_or_none(json_ld.get('episodeNumber')),
'description': unescapeHTML(json_ld.get('description')),
})
part_of_season = json_ld.get('partOfSeason')
if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason':
info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
part_of_series = json_ld.get('partOfSeries')
if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries':
info['series'] = unescapeHTML(part_of_series.get('name'))
elif item_type == 'Article':
info.update({
'timestamp': parse_iso8601(json_ld.get('datePublished')),
'title': unescapeHTML(json_ld.get('headline')),
'description': unescapeHTML(json_ld.get('articleBody')),
})
return dict((k, v) for k, v in info.items() if v is not None)
@staticmethod
def _hidden_inputs(html):
html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
@@ -788,6 +831,12 @@ class InfoExtractor(object):
if not formats:
raise ExtractorError('No video formats found')
for f in formats:
# Automatically determine tbr when missing based on abr and vbr (improves
# formats sorting in some cases)
if 'tbr' not in f and f.get('abr') is not None and f.get('vbr') is not None:
f['tbr'] = f['abr'] + f['vbr']
def _formats_key(f):
# TODO remove the following workaround
from ..utils import determine_ext
@@ -854,6 +903,16 @@ class InfoExtractor(object):
item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'),
formats)
@staticmethod
def _remove_duplicate_formats(formats):
format_urls = set()
unique_formats = []
for f in formats:
if f['url'] not in format_urls:
format_urls.add(f['url'])
unique_formats.append(f)
formats[:] = unique_formats
def _is_valid_url(self, url, video_id, item='video'):
url = self._proto_relative_url(url, scheme='http:')
# For now assume non HTTP(S) URLs always valid
@@ -977,6 +1036,28 @@ class InfoExtractor(object):
return []
m3u8_doc, urlh = res
m3u8_url = urlh.geturl()
# We should try extracting formats only from master playlists [1], i.e.
# playlists that describe available qualities. On the other hand media
# playlists [2] should be returned as is since they contain just the media
# without qualities renditions.
# Fortunately, master playlist can be easily distinguished from media
# playlist based on particular tags availability. As of [1, 2] master
# playlist tags MUST NOT appear in a media playist and vice versa.
# As of [3] #EXT-X-TARGETDURATION tag is REQUIRED for every media playlist
# and MUST NOT appear in master playlist thus we can clearly detect media
# playlist with this criterion.
# 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.4
# 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3
# 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1
if '#EXT-X-TARGETDURATION' in m3u8_doc: # media playlist, return as is
return [{
'url': m3u8_url,
'format_id': m3u8_id,
'ext': ext,
'protocol': entry_protocol,
'preference': preference,
}]
last_info = None
last_media = None
kv_rex = re.compile(
@@ -1016,19 +1097,29 @@ class InfoExtractor(object):
'protocol': entry_protocol,
'preference': preference,
}
codecs = last_info.get('CODECS')
if codecs:
# TODO: looks like video codec is not always necessarily goes first
va_codecs = codecs.split(',')
if va_codecs[0]:
f['vcodec'] = va_codecs[0].partition('.')[0]
if len(va_codecs) > 1 and va_codecs[1]:
f['acodec'] = va_codecs[1].partition('.')[0]
resolution = last_info.get('RESOLUTION')
if resolution:
width_str, height_str = resolution.split('x')
f['width'] = int(width_str)
f['height'] = int(height_str)
codecs = last_info.get('CODECS')
if codecs:
vcodec, acodec = [None] * 2
va_codecs = codecs.split(',')
if len(va_codecs) == 1:
# Audio only entries usually come with single codec and
# no resolution. For more robustness we also check it to
# be mp4 audio.
if not resolution and va_codecs[0].startswith('mp4a'):
vcodec, acodec = 'none', va_codecs[0]
else:
vcodec = va_codecs[0]
else:
vcodec, acodec = va_codecs[:2]
f.update({
'acodec': acodec,
'vcodec': vcodec,
})
if last_media is not None:
f['m3u8_media'] = last_media
last_media = None
@@ -1127,12 +1218,15 @@ class InfoExtractor(object):
formats = []
rtmp_count = 0
http_count = 0
m3u8_count = 0
srcs = []
videos = smil.findall(self._xpath_ns('.//video', namespace))
for video in videos:
src = video.get('src')
if not src:
if not src or src in srcs:
continue
srcs.append(src)
bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
filesize = int_or_none(video.get('size') or video.get('fileSize'))
@@ -1164,10 +1258,20 @@ class InfoExtractor(object):
continue
src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src)
src_url = src_url.strip()
if proto == 'm3u8' or src_ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
src_url, video_id, ext or 'mp4', m3u8_id='hls', fatal=False))
m3u8_formats = self._extract_m3u8_formats(
src_url, video_id, ext or 'mp4', m3u8_id='hls', fatal=False)
if len(m3u8_formats) == 1:
m3u8_count += 1
m3u8_formats[0].update({
'format_id': 'hls-%d' % (m3u8_count if bitrate is None else bitrate),
'tbr': bitrate,
'width': width,
'height': height,
})
formats.extend(m3u8_formats)
continue
if src_ext == 'f4m':
@@ -1200,21 +1304,14 @@ class InfoExtractor(object):
return formats
def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
urls = []
subtitles = {}
for num, textstream in enumerate(smil.findall(self._xpath_ns('.//textstream', namespace))):
src = textstream.get('src')
if not src:
if not src or src in urls:
continue
ext = textstream.get('ext') or determine_ext(src)
if not ext:
type_ = textstream.get('type')
SUBTITLES_TYPES = {
'text/vtt': 'vtt',
'text/srt': 'srt',
'application/smptett+xml': 'tt',
}
if type_ in SUBTITLES_TYPES:
ext = SUBTITLES_TYPES[type_]
urls.append(src)
ext = textstream.get('ext') or determine_ext(src) or mimetype2ext(textstream.get('type'))
lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang
subtitles.setdefault(lang, []).append({
'url': src,
@@ -1265,10 +1362,167 @@ class InfoExtractor(object):
})
return entries
def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}):
res = self._download_webpage_handle(
mpd_url, video_id,
note=note or 'Downloading MPD manifest',
errnote=errnote or 'Failed to download MPD manifest',
fatal=fatal)
if res is False:
return []
mpd, urlh = res
mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group()
return self._parse_mpd_formats(
compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict)
def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
if mpd_doc.get('type') == 'dynamic':
return []
namespace = self._search_regex(r'(?i)^{([^}]+)?}MPD$', mpd_doc.tag, 'namespace', default=None)
def _add_ns(path):
return self._xpath_ns(path, namespace)
def is_drm_protected(element):
return element.find(_add_ns('ContentProtection')) is not None
def extract_multisegment_info(element, ms_parent_info):
ms_info = ms_parent_info.copy()
segment_list = element.find(_add_ns('SegmentList'))
if segment_list is not None:
segment_urls_e = segment_list.findall(_add_ns('SegmentURL'))
if segment_urls_e:
ms_info['segment_urls'] = [segment.attrib['media'] for segment in segment_urls_e]
initialization = segment_list.find(_add_ns('Initialization'))
if initialization is not None:
ms_info['initialization_url'] = initialization.attrib['sourceURL']
else:
segment_template = element.find(_add_ns('SegmentTemplate'))
if segment_template is not None:
start_number = segment_template.get('startNumber')
if start_number:
ms_info['start_number'] = int(start_number)
segment_timeline = segment_template.find(_add_ns('SegmentTimeline'))
if segment_timeline is not None:
s_e = segment_timeline.findall(_add_ns('S'))
if s_e:
ms_info['total_number'] = 0
for s in s_e:
ms_info['total_number'] += 1 + int(s.get('r', '0'))
else:
timescale = segment_template.get('timescale')
if timescale:
ms_info['timescale'] = int(timescale)
segment_duration = segment_template.get('duration')
if segment_duration:
ms_info['segment_duration'] = int(segment_duration)
media_template = segment_template.get('media')
if media_template:
ms_info['media_template'] = media_template
initialization = segment_template.get('initialization')
if initialization:
ms_info['initialization_url'] = initialization
else:
initialization = segment_template.find(_add_ns('Initialization'))
if initialization is not None:
ms_info['initialization_url'] = initialization.attrib['sourceURL']
return ms_info
mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
formats = []
for period in mpd_doc.findall(_add_ns('Period')):
period_duration = parse_duration(period.get('duration')) or mpd_duration
period_ms_info = extract_multisegment_info(period, {
'start_number': 1,
'timescale': 1,
})
for adaptation_set in period.findall(_add_ns('AdaptationSet')):
if is_drm_protected(adaptation_set):
continue
adaption_set_ms_info = extract_multisegment_info(adaptation_set, period_ms_info)
for representation in adaptation_set.findall(_add_ns('Representation')):
if is_drm_protected(representation):
continue
representation_attrib = adaptation_set.attrib.copy()
representation_attrib.update(representation.attrib)
mime_type = representation_attrib.get('mimeType')
content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType')
if content_type == 'text':
# TODO implement WebVTT downloading
pass
elif content_type == 'video' or content_type == 'audio':
base_url = ''
for element in (representation, adaptation_set, period, mpd_doc):
base_url_e = element.find(_add_ns('BaseURL'))
if base_url_e is not None:
base_url = base_url_e.text + base_url
if re.match(r'^https?://', base_url):
break
if mpd_base_url and not re.match(r'^https?://', base_url):
if not mpd_base_url.endswith('/') and not base_url.startswith('/'):
mpd_base_url += '/'
base_url = mpd_base_url + base_url
representation_id = representation_attrib.get('id')
lang = representation_attrib.get('lang')
url_el = representation.find(_add_ns('BaseURL'))
filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength') if url_el is not None else None)
f = {
'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
'url': base_url,
'width': int_or_none(representation_attrib.get('width')),
'height': int_or_none(representation_attrib.get('height')),
'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000),
'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
'fps': int_or_none(representation_attrib.get('frameRate')),
'vcodec': 'none' if content_type == 'audio' else representation_attrib.get('codecs'),
'acodec': 'none' if content_type == 'video' else representation_attrib.get('codecs'),
'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
'format_note': 'DASH %s' % content_type,
'filesize': filesize,
}
representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
if 'segment_urls' not in representation_ms_info and 'media_template' in representation_ms_info:
if 'total_number' not in representation_ms_info and 'segment_duration':
segment_duration = float(representation_ms_info['segment_duration']) / float(representation_ms_info['timescale'])
representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
media_template = representation_ms_info['media_template']
media_template = media_template.replace('$RepresentationID$', representation_id)
media_template = re.sub(r'\$(Number|Bandwidth)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template)
media_template.replace('$$', '$')
representation_ms_info['segment_urls'] = [media_template % {'Number': segment_number, 'Bandwidth': representation_attrib.get('bandwidth')} for segment_number in range(representation_ms_info['start_number'], representation_ms_info['total_number'] + representation_ms_info['start_number'])]
if 'segment_urls' in representation_ms_info:
f.update({
'segment_urls': representation_ms_info['segment_urls'],
'protocol': 'http_dash_segments',
})
if 'initialization_url' in representation_ms_info:
initialization_url = representation_ms_info['initialization_url'].replace('$RepresentationID$', representation_id)
f.update({
'initialization_url': initialization_url,
})
if not f.get('url'):
f['url'] = initialization_url
try:
existing_format = next(
fo for fo in formats
if fo['format_id'] == representation_id)
except StopIteration:
full_info = formats_dict.get(representation_id, {}).copy()
full_info.update(f)
formats.append(full_info)
else:
existing_format.update(f)
else:
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
self._sort_formats(formats)
return formats
def _live_title(self, name):
""" Generate the title for a live video """
now = datetime.datetime.now()
now_str = now.strftime("%Y-%m-%d %H:%M")
now_str = now.strftime('%Y-%m-%d %H:%M')
return name + ' ' + now_str
def _int(self, v, name, fatal=False, **kwargs):
@@ -1341,7 +1595,7 @@ class InfoExtractor(object):
return {}
def _get_subtitles(self, *args, **kwargs):
raise NotImplementedError("This method must be implemented by subclasses")
raise NotImplementedError('This method must be implemented by subclasses')
@staticmethod
def _merge_subtitle_items(subtitle_list1, subtitle_list2):
@@ -1367,7 +1621,16 @@ class InfoExtractor(object):
return {}
def _get_automatic_captions(self, *args, **kwargs):
raise NotImplementedError("This method must be implemented by subclasses")
raise NotImplementedError('This method must be implemented by subclasses')
def mark_watched(self, *args, **kwargs):
if (self._downloader.params.get('mark_watched', False) and
(self._get_login_info()[0] is not None or
self._downloader.params.get('cookiefile') is not None)):
self._mark_watched(*args, **kwargs)
def _mark_watched(self, *args, **kwargs):
raise NotImplementedError('This method must be implemented by subclasses')
class SearchInfoExtractor(InfoExtractor):
@@ -1407,7 +1670,7 @@ class SearchInfoExtractor(InfoExtractor):
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
raise NotImplementedError("This method must be implemented by subclasses")
raise NotImplementedError('This method must be implemented by subclasses')
@property
def SEARCH_KEY(self):

View File

@@ -0,0 +1,95 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
class CrackleIE(InfoExtractor):
_VALID_URL = r'(?:crackle:|https?://(?:www\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
_TEST = {
'url': 'http://www.crackle.com/the-art-of-more/2496419',
'info_dict': {
'id': '2496419',
'ext': 'mp4',
'title': 'Heavy Lies the Head',
'description': 'md5:bb56aa0708fe7b9a4861535f15c3abca',
},
'params': {
# m3u8 download
'skip_download': True,
}
}
# extracted from http://legacyweb-us.crackle.com/flash/QueryReferrer.ashx
_SUBTITLE_SERVER = 'http://web-us-az.crackle.com'
_UPLYNK_OWNER_ID = 'e8773f7770a44dbd886eee4fca16a66b'
_THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614'
# extracted from http://legacyweb-us.crackle.com/flash/ReferrerRedirect.ashx
_MEDIA_FILE_SLOTS = {
'c544.flv': {
'width': 544,
'height': 306,
},
'360p.mp4': {
'width': 640,
'height': 360,
},
'480p.mp4': {
'width': 852,
'height': 478,
},
'480p_1mbps.mp4': {
'width': 852,
'height': 478,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
item = self._download_xml(
'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id,
video_id).find('i')
title = item.attrib['t']
thumbnail = None
subtitles = {}
formats = self._extract_m3u8_formats(
'http://content.uplynk.com/ext/%s/%s.m3u8' % (self._UPLYNK_OWNER_ID, video_id),
video_id, 'mp4', m3u8_id='hls', fatal=None)
path = item.attrib.get('p')
if path:
thumbnail = self._THUMBNAIL_TEMPLATE % path
http_base_url = 'http://ahttp.crackle.com/' + path
for mfs_path, mfs_info in self._MEDIA_FILE_SLOTS.items():
formats.append({
'url': http_base_url + mfs_path,
'format_id': 'http-' + mfs_path.split('.')[0],
'width': mfs_info['width'],
'height': mfs_info['height'],
})
for cc in item.findall('cc'):
locale = cc.attrib.get('l')
v = cc.attrib.get('v')
if locale and v:
if locale not in subtitles:
subtitles[locale] = []
subtitles[locale] = [{
'url': '%s/%s%s_%s.xml' % (self._SUBTITLE_SERVER, path, locale, v),
'ext': 'ttml',
}]
self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
return {
'id': video_id,
'title': title,
'description': item.attrib.get('d'),
'duration': int(item.attrib.get('r'), 16) if item.attrib.get('r') else None,
'series': item.attrib.get('sn'),
'season_number': int_or_none(item.attrib.get('se')),
'episode_number': int_or_none(item.attrib.get('ep')),
'thumbnail': thumbnail,
'subtitles': subtitles,
'formats': formats,
}

View File

@@ -180,40 +180,40 @@ class CrunchyrollIE(CrunchyrollBaseIE):
return assvalue
output = '[Script Info]\n'
output += 'Title: %s\n' % sub_root.attrib["title"]
output += 'Title: %s\n' % sub_root.attrib['title']
output += 'ScriptType: v4.00+\n'
output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"]
output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"]
output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"]
output += 'WrapStyle: %s\n' % sub_root.attrib['wrap_style']
output += 'PlayResX: %s\n' % sub_root.attrib['play_res_x']
output += 'PlayResY: %s\n' % sub_root.attrib['play_res_y']
output += """ScaledBorderAndShadow: yes
[V4+ Styles]
Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
"""
for style in sub_root.findall('./styles/style'):
output += 'Style: ' + style.attrib["name"]
output += ',' + style.attrib["font_name"]
output += ',' + style.attrib["font_size"]
output += ',' + style.attrib["primary_colour"]
output += ',' + style.attrib["secondary_colour"]
output += ',' + style.attrib["outline_colour"]
output += ',' + style.attrib["back_colour"]
output += ',' + ass_bool(style.attrib["bold"])
output += ',' + ass_bool(style.attrib["italic"])
output += ',' + ass_bool(style.attrib["underline"])
output += ',' + ass_bool(style.attrib["strikeout"])
output += ',' + style.attrib["scale_x"]
output += ',' + style.attrib["scale_y"]
output += ',' + style.attrib["spacing"]
output += ',' + style.attrib["angle"]
output += ',' + style.attrib["border_style"]
output += ',' + style.attrib["outline"]
output += ',' + style.attrib["shadow"]
output += ',' + style.attrib["alignment"]
output += ',' + style.attrib["margin_l"]
output += ',' + style.attrib["margin_r"]
output += ',' + style.attrib["margin_v"]
output += ',' + style.attrib["encoding"]
output += 'Style: ' + style.attrib['name']
output += ',' + style.attrib['font_name']
output += ',' + style.attrib['font_size']
output += ',' + style.attrib['primary_colour']
output += ',' + style.attrib['secondary_colour']
output += ',' + style.attrib['outline_colour']
output += ',' + style.attrib['back_colour']
output += ',' + ass_bool(style.attrib['bold'])
output += ',' + ass_bool(style.attrib['italic'])
output += ',' + ass_bool(style.attrib['underline'])
output += ',' + ass_bool(style.attrib['strikeout'])
output += ',' + style.attrib['scale_x']
output += ',' + style.attrib['scale_y']
output += ',' + style.attrib['spacing']
output += ',' + style.attrib['angle']
output += ',' + style.attrib['border_style']
output += ',' + style.attrib['outline']
output += ',' + style.attrib['shadow']
output += ',' + style.attrib['alignment']
output += ',' + style.attrib['margin_l']
output += ',' + style.attrib['margin_r']
output += ',' + style.attrib['margin_v']
output += ',' + style.attrib['encoding']
output += '\n'
output += """
@@ -222,15 +222,15 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
"""
for event in sub_root.findall('./events/event'):
output += 'Dialogue: 0'
output += ',' + event.attrib["start"]
output += ',' + event.attrib["end"]
output += ',' + event.attrib["style"]
output += ',' + event.attrib["name"]
output += ',' + event.attrib["margin_l"]
output += ',' + event.attrib["margin_r"]
output += ',' + event.attrib["margin_v"]
output += ',' + event.attrib["effect"]
output += ',' + event.attrib["text"]
output += ',' + event.attrib['start']
output += ',' + event.attrib['end']
output += ',' + event.attrib['style']
output += ',' + event.attrib['name']
output += ',' + event.attrib['margin_l']
output += ',' + event.attrib['margin_r']
output += ',' + event.attrib['margin_v']
output += ',' + event.attrib['effect']
output += ',' + event.attrib['text']
output += '\n'
return output
@@ -376,7 +376,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
IE_NAME = "crunchyroll:playlist"
IE_NAME = 'crunchyroll:playlist'
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)'
_TESTS = [{

View File

@@ -68,11 +68,16 @@ class CSpanIE(InfoExtractor):
video_type, video_id = matches.groups()
video_type = 'clip' if video_type == 'id' else 'program'
else:
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url:
title = self._og_search_title(webpage)
surl = smuggle_url(senate_isvp_url, {'force_title': title})
return self.url_result(surl, 'SenateISVP', video_id, title)
m = re.search(r'data-(?P<type>clip|prog)id=["\'](?P<id>\d+)', webpage)
if m:
video_id = m.group('id')
video_type = 'program' if m.group('type') == 'prog' else 'clip'
else:
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url:
title = self._og_search_title(webpage)
surl = smuggle_url(senate_isvp_url, {'force_title': title})
return self.url_result(surl, 'SenateISVP', video_id, title)
if video_type is None or video_id is None:
raise ExtractorError('unable to find video id and type')
@@ -107,6 +112,13 @@ class CSpanIE(InfoExtractor):
'height': int_or_none(get_text_attr(quality, 'height')),
'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
})
if not formats:
path = unescapeHTML(get_text_attr(f, 'path'))
if not path:
continue
formats = self._extract_m3u8_formats(
path, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }]
self._sort_formats(formats)
entries.append({
'id': '%s_%d' % (video_id, partnum + 1),

View File

@@ -0,0 +1,63 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import int_or_none
class CultureUnpluggedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cultureunplugged\.com/documentary/watch-online/play/(?P<id>\d+)(?:/(?P<display_id>[^/]+))?'
_TESTS = [{
'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662/The-Next--Best-West',
'md5': 'ac6c093b089f7d05e79934dcb3d228fc',
'info_dict': {
'id': '53662',
'display_id': 'The-Next--Best-West',
'ext': 'mp4',
'title': 'The Next, Best West',
'description': 'md5:0423cd00833dea1519cf014e9d0903b1',
'thumbnail': 're:^https?://.*\.jpg$',
'creator': 'Coldstream Creative',
'duration': 2203,
'view_count': int,
}
}, {
'url': 'http://www.cultureunplugged.com/documentary/watch-online/play/53662',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
movie_data = self._download_json(
'http://www.cultureunplugged.com/movie-data/cu-%s.json' % video_id, display_id)
video_url = movie_data['url']
title = movie_data['title']
description = movie_data.get('synopsis')
creator = movie_data.get('producer')
duration = int_or_none(movie_data.get('duration'))
view_count = int_or_none(movie_data.get('views'))
thumbnails = [{
'url': movie_data['%s_thumb' % size],
'id': size,
'preference': preference,
} for preference, size in enumerate((
'small', 'large')) if movie_data.get('%s_thumb' % size)]
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
'description': description,
'creator': creator,
'duration': duration,
'view_count': view_count,
'thumbnails': thumbnails,
}

View File

@@ -37,7 +37,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
class DailymotionIE(DailymotionBaseInfoExtractor):
_VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
_VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:embed|swf|#)/)?video/(?P<id>[^/?_]+)'
IE_NAME = 'dailymotion'
_FORMATS = [
@@ -104,6 +104,10 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
{
'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
'only_matching': True,
},
{
'url': 'http://www.dailymotion.com/swf/video/x3n92nf',
'only_matching': True,
}
]
@@ -118,10 +122,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
description = self._og_search_description(webpage) or self._html_search_meta(
'description', webpage, 'description')
view_count = str_to_int(self._search_regex(
[r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:(\d+)"',
r'video_views_count[^>]+>\s+([\d\.,]+)'],
webpage, 'view count', fatal=False))
view_count_str = self._search_regex(
(r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([\s\d,.]+)"',
r'video_views_count[^>]+>\s+([\s\d\,.]+)'),
webpage, 'view count', fatal=False)
if view_count_str:
view_count_str = re.sub(r'\s', '', view_count_str)
view_count = str_to_int(view_count_str)
comment_count = int_or_none(self._search_regex(
r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
webpage, 'comment count', fatal=False))
@@ -336,7 +343,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
class DailymotionUserIE(DailymotionPlaylistIE):
IE_NAME = 'dailymotion:user'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
_PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
_TESTS = [{
'url': 'https://www.dailymotion.com/user/nqtv',
@@ -392,13 +399,13 @@ class DailymotionCloudIE(DailymotionBaseInfoExtractor):
}]
@classmethod
def _extract_dmcloud_url(self, webpage):
mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage)
def _extract_dmcloud_url(cls, webpage):
mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, webpage)
if mobj:
return mobj.group(1)
mobj = re.search(
r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL,
r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL,
webpage)
if mobj:
return mobj.group(1)

View File

@@ -2,17 +2,26 @@
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..compat import (
compat_parse_qs,
compat_urllib_parse,
compat_urllib_parse_unquote,
compat_urlparse,
)
from ..utils import (
int_or_none,
str_to_int,
xpath_text,
unescapeHTML,
)
class DaumIE(InfoExtractor):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/v/(?P<id>[^?#&]+)'
_VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
IE_NAME = 'daum.net'
_TESTS = [{
@@ -23,25 +32,57 @@ class DaumIE(InfoExtractor):
'title': '마크 헌트 vs 안토니오 실바',
'description': 'Mark Hunt vs Antonio Silva',
'upload_date': '20131217',
'thumbnail': 're:^https?://.*\.(?:jpg|png)',
'duration': 2117,
'view_count': int,
'comment_count': int,
},
}, {
'url': 'http://m.tvpot.daum.net/v/65139429',
'info_dict': {
'id': '65139429',
'ext': 'mp4',
'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118',
'description': 'md5:79794514261164ff27e36a21ad229fc5',
'upload_date': '20150604',
'thumbnail': 're:^https?://.*\.(?:jpg|png)',
'duration': 154,
'view_count': int,
'comment_count': int,
},
}, {
'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
'only_matching': True,
}, {
'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
'info_dict': {
'id': 'vwIpVpCQsT8$',
'ext': 'flv',
'title': '01-Korean War ( Trouble on the horizon )',
'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
'upload_date': '20080223',
'thumbnail': 're:^https?://.*\.(?:jpg|png)',
'duration': 249,
'view_count': int,
'comment_count': int,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_id = compat_urllib_parse_unquote(self._match_id(url))
query = compat_urllib_parse.urlencode({'vid': video_id})
info = self._download_xml(
'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
'Downloading video info')
movie_data = self._download_json(
'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query,
video_id, 'Downloading video formats info')
# For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
info = self._download_xml(
'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
'Downloading video info')
formats = []
for format_el in movie_data['output_list']['output_list']:
profile = format_el['profile']
@@ -76,8 +117,9 @@ class DaumIE(InfoExtractor):
class DaumClipIE(InfoExtractor):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.do|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
IE_NAME = 'daum.net:clip'
_URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s'
_TESTS = [{
'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
@@ -87,11 +129,19 @@ class DaumClipIE(InfoExtractor):
'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
'upload_date': '20130831',
'thumbnail': 're:^https?://.*\.(?:jpg|png)',
'duration': 3868,
'view_count': int,
},
}, {
'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if DaumPlaylistIE.suitable(url) or DaumUserIE.suitable(url) else super(DaumClipIE, cls).suitable(url)
def _real_extract(self, url):
video_id = self._match_id(url)
clip_info = self._download_json(
@@ -102,7 +152,7 @@ class DaumClipIE(InfoExtractor):
'_type': 'url_transparent',
'id': video_id,
'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
'title': clip_info['title'],
'title': unescapeHTML(clip_info['title']),
'thumbnail': clip_info.get('thumb_url'),
'description': clip_info.get('contents'),
'duration': int_or_none(clip_info.get('duration')),
@@ -110,3 +160,139 @@ class DaumClipIE(InfoExtractor):
'view_count': int_or_none(clip_info.get('play_count')),
'ie_key': 'Daum',
}
class DaumListIE(InfoExtractor):
def _get_entries(self, list_id, list_id_type):
name = None
entries = []
for pagenum in itertools.count(1):
list_info = self._download_json(
'http://tvpot.daum.net/mypot/json/GetClipInfo.do?size=48&init=true&order=date&page=%d&%s=%s' % (
pagenum, list_id_type, list_id), list_id, 'Downloading list info - %s' % pagenum)
entries.extend([
self.url_result(
'http://tvpot.daum.net/v/%s' % clip['vid'])
for clip in list_info['clip_list']
])
if not name:
name = list_info.get('playlist_bean', {}).get('name') or \
list_info.get('potInfo', {}).get('name')
if not list_info.get('has_more'):
break
return name, entries
def _check_clip(self, url, list_id):
query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query)
if 'clipid' in query_dict:
clip_id = query_dict['clipid'][0]
if self._downloader.params.get('noplaylist'):
self.to_screen('Downloading just video %s because of --no-playlist' % clip_id)
return self.url_result(DaumClipIE._URL_TEMPLATE % clip_id, 'DaumClip')
else:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
class DaumPlaylistIE(DaumListIE):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View\.do|Top\.tv)\?.*?playlistid=(?P<id>[0-9]+)'
IE_NAME = 'daum.net:playlist'
_URL_TEMPLATE = 'http://tvpot.daum.net/mypot/View.do?playlistid=%s'
_TESTS = [{
'note': 'Playlist url with clipid',
'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
'info_dict': {
'id': '6213966',
'title': 'Woorissica Official',
},
'playlist_mincount': 181
}, {
'note': 'Playlist url with clipid - noplaylist',
'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844',
'info_dict': {
'id': '73806844',
'ext': 'mp4',
'title': '151017 Airport',
'upload_date': '20160117',
},
'params': {
'noplaylist': True,
'skip_download': True,
}
}]
@classmethod
def suitable(cls, url):
return False if DaumUserIE.suitable(url) else super(DaumPlaylistIE, cls).suitable(url)
def _real_extract(self, url):
list_id = self._match_id(url)
clip_result = self._check_clip(url, list_id)
if clip_result:
return clip_result
name, entries = self._get_entries(list_id, 'playlistid')
return self.playlist_result(entries, list_id, name)
class DaumUserIE(DaumListIE):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View|Top)\.(?:do|tv)\?.*?ownerid=(?P<id>[0-9a-zA-Z]+)'
IE_NAME = 'daum.net:user'
_TESTS = [{
'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0',
'info_dict': {
'id': 'o2scDLIVbHc0',
'title': '마이 리틀 텔레비전',
},
'playlist_mincount': 213
}, {
'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156',
'info_dict': {
'id': '73801156',
'ext': 'mp4',
'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116',
'upload_date': '20160117',
'description': 'md5:5e91d2d6747f53575badd24bd62b9f36'
},
'params': {
'noplaylist': True,
'skip_download': True,
}
}, {
'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence',
'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631',
'info_dict': {
'id': '6196631',
'title': '마이 리틀 텔레비전 - 20160109',
},
'playlist_count': 11
}, {
'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0',
'only_matching': True,
}, {
'url': 'http://m.tvpot.daum.net/mypot/Top.tv?ownerid=45x1okb1If50&playlistid=3569733',
'only_matching': True,
}]
def _real_extract(self, url):
list_id = self._match_id(url)
clip_result = self._check_clip(url, list_id)
if clip_result:
return clip_result
query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query)
if 'playlistid' in query_dict:
playlist_id = query_dict['playlistid'][0]
return self.url_result(DaumPlaylistIE._URL_TEMPLATE % playlist_id, 'DaumPlaylist')
name, entries = self._get_entries(list_id, 'ownerid')
return self.playlist_result(entries, list_id, name)

View File

@@ -7,9 +7,9 @@ from .common import InfoExtractor
from ..utils import int_or_none
class UltimediaIE(InfoExtractor):
class DigitekaIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:www\.)?ultimedia\.com/
https?://(?:www\.)?(?:digiteka\.net|ultimedia\.com)/
(?:
deliver/
(?P<embed_type>
@@ -56,6 +56,9 @@ class UltimediaIE(InfoExtractor):
'timestamp': 1424760500,
'uploader_id': '3rfzk',
},
}, {
'url': 'https://www.digiteka.net/deliver/generic/iframe/mdtk/01637594/src/lqm3kl/zone/1/showtitle/1/autoplay/yes',
'only_matching': True,
}]
@staticmethod

View File

@@ -18,7 +18,7 @@ class DouyuTVIE(InfoExtractor):
'display_id': 'iseven',
'ext': 'flv',
'title': 're:^清晨醒脑T-ara根本停不下来 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'md5:c93d6692dde6fe33809a46edcbecca44',
'description': 'md5:f34981259a03e980a3c6404190a3ed61',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': '7师傅',
'uploader_id': '431925',
@@ -26,7 +26,7 @@ class DouyuTVIE(InfoExtractor):
},
'params': {
'skip_download': True,
}
},
}, {
'url': 'http://www.douyutv.com/85982',
'info_dict': {
@@ -42,7 +42,24 @@ class DouyuTVIE(InfoExtractor):
},
'params': {
'skip_download': True,
}
},
'skip': 'Romm not found',
}, {
'url': 'http://www.douyutv.com/17732',
'info_dict': {
'id': '17732',
'display_id': '17732',
'ext': 'flv',
'title': 're:^清晨醒脑T-ara根本停不下来 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'md5:f34981259a03e980a3c6404190a3ed61',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': '7师傅',
'uploader_id': '431925',
'is_live': True,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):

View File

@@ -1,6 +1,8 @@
# encoding: utf-8
# coding: utf-8
from __future__ import unicode_literals
import json
import re
import time
from .common import InfoExtractor
@@ -8,44 +10,125 @@ from ..utils import int_or_none
class DPlayIE(InfoExtractor):
_VALID_URL = r'http://www\.dplay\.se/[^/]+/(?P<id>[^/?#]+)'
_VALID_URL = r'http://(?P<domain>it\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P<id>[^/?#]+)'
_TEST = {
_TESTS = [{
'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/',
'info_dict': {
'id': '1255600',
'display_id': 'stagione-1-episodio-25',
'ext': 'mp4',
'title': 'Episodio 25',
'description': 'md5:cae5f40ad988811b197d2d27a53227eb',
'duration': 2761,
'timestamp': 1454701800,
'upload_date': '20160205',
'creator': 'RTIT',
'series': 'Take me out',
'season_number': 1,
'episode_number': 25,
'age_limit': 0,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
'info_dict': {
'id': '3172',
'ext': 'mp4',
'display_id': 'season-1-svensken-lar-sig-njuta-av-livet',
'ext': 'flv',
'title': 'Svensken lär sig njuta av livet',
'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8',
'duration': 2650,
'timestamp': 1365454320,
'upload_date': '20130408',
'creator': 'Kanal 5 (Home)',
'series': 'Nugammalt - 77 händelser som format Sverige',
'season_number': 1,
'episode_number': 1,
'age_limit': 0,
},
}
}, {
'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/',
'info_dict': {
'id': '70816',
'display_id': 'season-6-episode-12',
'ext': 'flv',
'title': 'Episode 12',
'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90',
'duration': 2563,
'timestamp': 1429696800,
'upload_date': '20150422',
'creator': 'Kanal 4',
'series': 'Mig og min mor',
'season_number': 6,
'episode_number': 12,
'age_limit': 0,
},
}, {
'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
domain = mobj.group('domain')
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'data-video-id="(\d+)"', webpage, 'video id')
r'data-video-id=["\'](\d+)', webpage, 'video id')
info = self._download_json(
'http://www.dplay.se/api/v2/ajax/videos?video_id=' + video_id,
'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id),
video_id)['data'][0]
self._set_cookie(
'secure.dplay.se', 'dsc-geo',
'{"countryCode":"NL","expiry":%d}' % ((time.time() + 20 * 60) * 1000))
# TODO: consider adding support for 'stream_type=hds', it seems to
# require setting some cookies
manifest_url = self._download_json(
'https://secure.dplay.se/secure/api/v2/user/authorization/stream/%s?stream_type=hls' % video_id,
video_id, 'Getting manifest url for hls stream')['hls']
formats = self._extract_m3u8_formats(
manifest_url, video_id, ext='mp4', entry_protocol='m3u8_native')
title = info['title']
PROTOCOLS = ('hls', 'hds')
formats = []
def extract_formats(protocol, manifest_url):
if protocol == 'hls':
formats.extend(self._extract_m3u8_formats(
manifest_url, video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False))
elif protocol == 'hds':
formats.extend(self._extract_f4m_formats(
manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0',
video_id, f4m_id=protocol, fatal=False))
domain_tld = domain.split('.')[-1]
if domain_tld in ('se', 'dk'):
for protocol in PROTOCOLS:
self._set_cookie(
'secure.dplay.%s' % domain_tld, 'dsc-geo',
json.dumps({
'countryCode': domain_tld.upper(),
'expiry': (time.time() + 20 * 60) * 1000,
}))
stream = self._download_json(
'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s'
% (domain_tld, video_id, protocol), video_id,
'Downloading %s stream JSON' % protocol, fatal=False)
if stream and stream.get(protocol):
extract_formats(protocol, stream[protocol])
else:
for protocol in PROTOCOLS:
if info.get(protocol):
extract_formats(protocol, info[protocol])
return {
'id': video_id,
'display_id': display_id,
'title': info['title'],
'formats': formats,
'title': title,
'description': info.get('video_metadata_longDescription'),
'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
'timestamp': int_or_none(info.get('video_publish_date')),
'creator': info.get('video_metadata_homeChannel'),
'series': info.get('video_metadata_show'),
'season_number': int_or_none(info.get('season')),
'episode_number': int_or_none(info.get('episode')),
'age_limit': int_or_none(info.get('minimum_age')),
'formats': formats,
}

View File

@@ -87,7 +87,7 @@ class DRBonanzaIE(InfoExtractor):
formats = []
for file in info['Files']:
if info['Type'] == "Video":
if info['Type'] == 'Video':
if file['Type'] in video_types:
format = parse_filename_info(file['Location'])
format.update({
@@ -101,10 +101,10 @@ class DRBonanzaIE(InfoExtractor):
if '/bonanza/' in rtmp_url:
format['play_path'] = rtmp_url.split('/bonanza/')[1]
formats.append(format)
elif file['Type'] == "Thumb":
elif file['Type'] == 'Thumb':
thumbnail = file['Location']
elif info['Type'] == "Audio":
if file['Type'] == "Audio":
elif info['Type'] == 'Audio':
if file['Type'] == 'Audio':
format = parse_filename_info(file['Location'])
format.update({
'url': file['Location'],
@@ -112,7 +112,7 @@ class DRBonanzaIE(InfoExtractor):
'vcodec': 'none',
})
formats.append(format)
elif file['Type'] == "Thumb":
elif file['Type'] == 'Thumb':
thumbnail = file['Location']
description = '%s\n%s\n%s\n' % (

View File

@@ -91,7 +91,7 @@ class DRTVIE(InfoExtractor):
subtitles_list = asset.get('SubtitlesList')
if isinstance(subtitles_list, list):
LANGS = {
'Danish': 'dk',
'Danish': 'da',
}
for subs in subtitles_list:
lang = subs['Language']

View File

@@ -17,85 +17,85 @@ class EightTracksIE(InfoExtractor):
IE_NAME = '8tracks'
_VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
_TEST = {
"name": "EightTracks",
"url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
"info_dict": {
'name': 'EightTracks',
'url': 'http://8tracks.com/ytdl/youtube-dl-test-tracks-a',
'info_dict': {
'id': '1336550',
'display_id': 'youtube-dl-test-tracks-a',
"description": "test chars: \"'/\\ä↭",
"title": "youtube-dl test tracks \"'/\\ä↭<>",
'description': "test chars: \"'/\\ä↭",
'title': "youtube-dl test tracks \"'/\\ä↭<>",
},
"playlist": [
'playlist': [
{
"md5": "96ce57f24389fc8734ce47f4c1abcc55",
"info_dict": {
"id": "11885610",
"ext": "m4a",
"title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
'md5': '96ce57f24389fc8734ce47f4c1abcc55',
'info_dict': {
'id': '11885610',
'ext': 'm4a',
'title': "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
'uploader_id': 'ytdl'
}
},
{
"md5": "4ab26f05c1f7291ea460a3920be8021f",
"info_dict": {
"id": "11885608",
"ext": "m4a",
"title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
'md5': '4ab26f05c1f7291ea460a3920be8021f',
'info_dict': {
'id': '11885608',
'ext': 'm4a',
'title': "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
'uploader_id': 'ytdl'
}
},
{
"md5": "d30b5b5f74217410f4689605c35d1fd7",
"info_dict": {
"id": "11885679",
"ext": "m4a",
"title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
'md5': 'd30b5b5f74217410f4689605c35d1fd7',
'info_dict': {
'id': '11885679',
'ext': 'm4a',
'title': "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
'uploader_id': 'ytdl'
}
},
{
"md5": "4eb0a669317cd725f6bbd336a29f923a",
"info_dict": {
"id": "11885680",
"ext": "m4a",
"title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
'md5': '4eb0a669317cd725f6bbd336a29f923a',
'info_dict': {
'id': '11885680',
'ext': 'm4a',
'title': "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
'uploader_id': 'ytdl'
}
},
{
"md5": "1893e872e263a2705558d1d319ad19e8",
"info_dict": {
"id": "11885682",
"ext": "m4a",
"title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
'md5': '1893e872e263a2705558d1d319ad19e8',
'info_dict': {
'id': '11885682',
'ext': 'm4a',
'title': "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
'uploader_id': 'ytdl'
}
},
{
"md5": "b673c46f47a216ab1741ae8836af5899",
"info_dict": {
"id": "11885683",
"ext": "m4a",
"title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
'md5': 'b673c46f47a216ab1741ae8836af5899',
'info_dict': {
'id': '11885683',
'ext': 'm4a',
'title': "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
'uploader_id': 'ytdl'
}
},
{
"md5": "1d74534e95df54986da7f5abf7d842b7",
"info_dict": {
"id": "11885684",
"ext": "m4a",
"title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
'md5': '1d74534e95df54986da7f5abf7d842b7',
'info_dict': {
'id': '11885684',
'ext': 'm4a',
'title': "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
'uploader_id': 'ytdl'
}
},
{
"md5": "f081f47af8f6ae782ed131d38b9cd1c0",
"info_dict": {
"id": "11885685",
"ext": "m4a",
"title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
'md5': 'f081f47af8f6ae782ed131d38b9cd1c0',
'info_dict': {
'id': '11885685',
'ext': 'm4a',
'title': "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
'uploader_id': 'ytdl'
}
}
]

View File

@@ -72,7 +72,7 @@ class EllenTVClipsIE(InfoExtractor):
def _extract_playlist(self, webpage):
json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
try:
return json.loads("[{" + json_string + "}]")
return json.loads('[{' + json_string + '}]')
except ValueError as ve:
raise ExtractorError('Failed to download JSON', cause=ve)

View File

@@ -9,7 +9,7 @@ class ElPaisIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])'
IE_DESC = 'El País'
_TEST = {
_TESTS = [{
'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html',
'md5': '98406f301f19562170ec071b83433d55',
'info_dict': {
@@ -19,30 +19,41 @@ class ElPaisIE(InfoExtractor):
'description': 'De lunes a viernes, a partir de las ocho de la mañana, Iñaki Gabilondo nos cuenta su visión de la actualidad nacional e internacional.',
'upload_date': '20140206',
}
}
}, {
'url': 'http://elcomidista.elpais.com/elcomidista/2016/02/24/articulo/1456340311_668921.html#?id_externo_nwl=newsletter_diaria20160303t',
'md5': '3bd5b09509f3519d7d9e763179b013de',
'info_dict': {
'id': '1456340311_668921',
'ext': 'mp4',
'title': 'Cómo hacer el mejor café con cafetera italiana',
'description': 'Que sí, que las cápsulas son cómodas. Pero si le pides algo más a la vida, quizá deberías aprender a usar bien la cafetera italiana. No tienes más que ver este vídeo y seguir sus siete normas básicas.',
'upload_date': '20160303',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
prefix = self._html_search_regex(
r'var url_cache = "([^"]+)";', webpage, 'URL prefix')
r'var\s+url_cache\s*=\s*"([^"]+)";', webpage, 'URL prefix')
video_suffix = self._search_regex(
r"URLMediaFile = url_cache \+ '([^']+)'", webpage, 'video URL')
r"(?:URLMediaFile|urlVideo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", webpage, 'video URL')
video_url = prefix + video_suffix
thumbnail_suffix = self._search_regex(
r"URLMediaStill = url_cache \+ '([^']+)'", webpage, 'thumbnail URL',
fatal=False)
r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'",
webpage, 'thumbnail URL', fatal=False)
thumbnail = (
None if thumbnail_suffix is None
else prefix + thumbnail_suffix)
title = self._html_search_regex(
'<h2 class="entry-header entry-title.*?>(.*?)</h2>',
(r"tituloVideo\s*=\s*'([^']+)'", webpage, 'title',
r'<h2 class="entry-header entry-title.*?>(.*?)</h2>'),
webpage, 'title')
date_str = self._search_regex(
upload_date = unified_strdate(self._search_regex(
r'<p class="date-header date-int updated"\s+title="([^"]+)">',
webpage, 'upload date', fatal=False)
upload_date = (None if date_str is None else unified_strdate(date_str))
webpage, 'upload date', default=None) or self._html_search_meta(
'datePublished', webpage, 'timestamp'))
return {
'id': video_id,

View File

@@ -1,21 +1,13 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
url_basename,
)
class EngadgetIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://www.engadget.com/
(?:video(?:/5min)?/(?P<id>\d+)|
[\d/]+/.*?)
'''
_VALID_URL = r'https?://www.engadget.com/video/(?P<id>\d+)'
_TEST = {
'url': 'http://www.engadget.com/video/5min/518153925/',
'url': 'http://www.engadget.com/video/518153925/',
'md5': 'c6820d4828a5064447a4d9fc73f312c9',
'info_dict': {
'id': '518153925',
@@ -27,15 +19,4 @@ class EngadgetIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
if video_id is not None:
return self.url_result('5min:%s' % video_id)
else:
title = url_basename(url)
webpage = self._download_webpage(url, title)
ids = re.findall(r'<iframe[^>]+?playList=(\d+)', webpage)
return {
'_type': 'playlist',
'title': title,
'entries': [self.url_result('5min:%s' % vid) for vid in ids]
}
return self.url_result('5min:%s' % video_id)

View File

@@ -53,8 +53,8 @@ class ESPNIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video_id = self._search_regex(
r'class="video-play-button"[^>]+data-id="(\d+)',
webpage, 'video id')
r'class=(["\']).*?video-play-button.*?\1[^>]+data-id=["\'](?P<id>\d+)',
webpage, 'video id', group='id')
cms = 'espn'
if 'data-source="intl"' in webpage:

View File

@@ -14,14 +14,14 @@ class EveryonesMixtapeIE(InfoExtractor):
_TESTS = [{
'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5',
"info_dict": {
'info_dict': {
'id': '5bfseWNmlds',
'ext': 'mp4',
"title": "Passion Pit - \"Sleepyhead\" (Official Music Video)",
"uploader": "FKR.TV",
"uploader_id": "frenchkissrecords",
"description": "Music video for \"Sleepyhead\" from Passion Pit's debut EP Chunk Of Change.\nBuy on iTunes: https://itunes.apple.com/us/album/chunk-of-change-ep/id300087641\n\nDirected by The Wilderness.\n\nhttp://www.passionpitmusic.com\nhttp://www.frenchkissrecords.com",
"upload_date": "20081015"
'title': "Passion Pit - \"Sleepyhead\" (Official Music Video)",
'uploader': 'FKR.TV',
'uploader_id': 'frenchkissrecords',
'description': "Music video for \"Sleepyhead\" from Passion Pit's debut EP Chunk Of Change.\nBuy on iTunes: https://itunes.apple.com/us/album/chunk-of-change-ep/id300087641\n\nDirected by The Wilderness.\n\nhttp://www.passionpitmusic.com\nhttp://www.frenchkissrecords.com",
'upload_date': '20081015'
},
'params': {
'skip_download': True, # This is simply YouTube

View File

@@ -41,7 +41,7 @@ class ExfmIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
song_id = mobj.group('id')
info_url = "http://ex.fm/api/v3/song/%s" % song_id
info_url = 'http://ex.fm/api/v3/song/%s' % song_id
info = self._download_json(info_url, song_id)['song']
song_url = info['url']
if re.match(self._SOUNDCLOUD_URL, song_url) is not None:

View File

@@ -6,9 +6,11 @@ import socket
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_http_client,
compat_urllib_error,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
)
from ..utils import (
error_to_compat_str,
@@ -23,19 +25,31 @@ from ..utils import (
class FacebookIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:\w+\.)?facebook\.com/
(?:[^#]*?\#!/)?
(?:
(?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
(?:v|video_id)=|
[^/]+/videos/(?:[^/]+/)?
)
(?P<id>[0-9]+)
(?:.*)'''
(?:
https?://
(?:\w+\.)?facebook\.com/
(?:[^#]*?\#!/)?
(?:
(?:
video/video\.php|
photo\.php|
video\.php|
video/embed|
story\.php
)\?(?:.*?)(?:v|video_id|story_fbid)=|
[^/]+/videos/(?:[^/]+/)?
)|
facebook:
)
(?P<id>[0-9]+)
'''
_LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
_CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
_NETRC_MACHINE = 'facebook'
IE_NAME = 'facebook'
_CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'
_TESTS = [{
'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
'md5': '6a40d33c0eccbb1af76cf0485a052659',
@@ -57,6 +71,16 @@ class FacebookIE(InfoExtractor):
'expected_warnings': [
'title'
]
}, {
'note': 'Video with DASH manifest',
'url': 'https://www.facebook.com/video.php?v=957955867617029',
'md5': '54706e4db4f5ad58fbad82dde1f1213f',
'info_dict': {
'id': '957955867617029',
'ext': 'mp4',
'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...',
'uploader': 'Demy de Zeeuw',
},
}, {
'url': 'https://www.facebook.com/video.php?v=10204634152394104',
'only_matching': True,
@@ -66,6 +90,12 @@ class FacebookIE(InfoExtractor):
}, {
'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater',
'only_matching': True,
}, {
'url': 'facebook:544765982287235',
'only_matching': True,
}, {
'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903',
'only_matching': True,
}]
def _login(self):
@@ -136,13 +166,36 @@ class FacebookIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
webpage = self._download_webpage(url, video_id)
req = sanitized_Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
req.add_header('User-Agent', self._CHROME_USER_AGENT)
webpage = self._download_webpage(req, video_id)
video_data = None
BEFORE = '{swf.addParam(param[0], param[1]);});\n'
AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
if not m:
if m:
data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse_unquote(data['params'])
video_data = json.loads(params_raw)['video_data']
def video_data_list2dict(video_data):
ret = {}
for item in video_data:
format_id = item['stream_type']
ret.setdefault(format_id, []).append(item)
return ret
if not video_data:
server_js_data = self._parse_json(self._search_regex(
r'handleServerJS\(({.+})\);', webpage, 'server js data'), video_id)
for item in server_js_data.get('instances', []):
if item[1][0] == 'VideoConfig':
video_data = video_data_list2dict(item[2][0]['videoData'])
break
if not video_data:
m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
if m_msg is not None:
raise ExtractorError(
@@ -150,26 +203,32 @@ class FacebookIE(InfoExtractor):
expected=True)
else:
raise ExtractorError('Cannot parse data')
data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse_unquote(data['params'])
params = json.loads(params_raw)
formats = []
for format_id, f in params['video_data'].items():
for format_id, f in video_data.items():
if not f or not isinstance(f, list):
continue
for quality in ('sd', 'hd'):
for src_type in ('src', 'src_no_ratelimit'):
src = f[0].get('%s_%s' % (quality, src_type))
if src:
preference = -10 if format_id == 'progressive' else 0
if quality == 'hd':
preference += 5
formats.append({
'format_id': '%s_%s_%s' % (format_id, quality, src_type),
'url': src,
'preference': -10 if format_id == 'progressive' else 0,
'preference': preference,
})
dash_manifest = f[0].get('dash_manifest')
if dash_manifest:
formats.extend(self._parse_mpd_formats(
compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest))))
if not formats:
raise ExtractorError('Cannot find video formats')
self._sort_formats(formats)
video_title = self._html_search_regex(
r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title',
default=None)
@@ -188,3 +247,33 @@ class FacebookIE(InfoExtractor):
'formats': formats,
'uploader': uploader,
}
class FacebookPostIE(InfoExtractor):
IE_NAME = 'facebook:post'
_VALID_URL = r'https?://(?:\w+\.)?facebook\.com/[^/]+/posts/(?P<id>\d+)'
_TEST = {
'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
'info_dict': {
'id': '544765982287235',
'ext': 'mp4',
'title': '"What are you doing running in the snow?"',
'uploader': 'FailArmy',
}
}
def _real_extract(self, url):
post_id = self._match_id(url)
webpage = self._download_webpage(url, post_id)
entries = [
self.url_result('facebook:%s' % video_id, FacebookIE.ie_key())
for video_id in self._parse_json(
self._search_regex(
r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])',
webpage, 'video ids', group='ids'),
post_id)]
return self.playlist_result(entries, post_id)

View File

@@ -52,7 +52,7 @@ class FazIE(InfoExtractor):
formats = []
for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
encoding = xpath_element(encodings, code)
if encoding:
if encoding is not None:
encoding_url = xpath_text(encoding, 'FILENAME')
if encoding_url:
formats.append({

View File

@@ -87,7 +87,7 @@ class FC2IE(InfoExtractor):
mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
info_url = (
"http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&".
'http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&'.
format(video_id, mimi, compat_urllib_request.quote(refer, safe=b'').replace('.', '%2E')))
info_webpage = self._download_webpage(

View File

@@ -1,5 +1,7 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
@@ -16,12 +18,7 @@ from ..utils import (
class FiveMinIE(InfoExtractor):
IE_NAME = '5min'
_VALID_URL = r'''(?x)
(?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?:.*?&)?playList=|
https?://(?:(?:massively|www)\.)?joystiq\.com/video/|
5min:)
(?P<id>\d+)
'''
_VALID_URL = r'(?:5min:(?P<id>\d+)(?::(?P<sid>\d+))?|https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?P<query>.*))'
_TESTS = [
{
@@ -45,6 +42,7 @@ class FiveMinIE(InfoExtractor):
'title': 'How to Make a Next-Level Fruit Salad',
'duration': 184,
},
'skip': 'no longer available',
},
]
_ERRORS = {
@@ -91,20 +89,33 @@ class FiveMinIE(InfoExtractor):
}
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
sid = mobj.group('sid')
if mobj.group('query'):
qs = compat_parse_qs(mobj.group('query'))
if not qs.get('playList'):
raise ExtractorError('Invalid URL', expected=True)
video_id = qs['playList'][0]
if qs.get('sid'):
sid = qs['sid'][0]
embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
embed_page = self._download_webpage(embed_url, video_id,
'Downloading embed page')
sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
query = compat_urllib_parse.urlencode({
'func': 'GetResults',
'playlist': video_id,
'sid': sid,
'isPlayerSeed': 'true',
'url': embed_url,
})
if not sid:
embed_page = self._download_webpage(embed_url, video_id,
'Downloading embed page')
sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
response = self._download_json(
'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
'https://syn.5min.com/handlers/SenseHandler.ashx?' +
compat_urllib_parse.urlencode({
'func': 'GetResults',
'playlist': video_id,
'sid': sid,
'isPlayerSeed': 'true',
'url': embed_url,
}),
video_id)
if not response['success']:
raise ExtractorError(
@@ -118,9 +129,7 @@ class FiveMinIE(InfoExtractor):
parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs(
compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0])
for rendition in info['Renditions']:
if rendition['RenditionType'] == 'm3u8':
formats.extend(self._extract_m3u8_formats(rendition['Url'], video_id, m3u8_id='hls'))
elif rendition['RenditionType'] == 'aac':
if rendition['RenditionType'] == 'aac' or rendition['RenditionType'] == 'm3u8':
continue
else:
rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType'])))

View File

@@ -9,6 +9,7 @@ class FOXIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.fox.com/watch/255180355939/7684182528',
'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
'info_dict': {
'id': '255180355939',
'ext': 'mp4',
@@ -17,10 +18,6 @@ class FOXIE(InfoExtractor):
'duration': 129,
},
'add_ie': ['ThePlatform'],
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
@@ -29,7 +26,7 @@ class FOXIE(InfoExtractor):
release_url = self._parse_json(self._search_regex(
r'"fox_pdk_player"\s*:\s*({[^}]+?})', webpage, 'fox_pdk_player'),
video_id)['release_url'] + '&manifest=m3u'
video_id)['release_url'] + '&switch=http'
return {
'_type': 'url_transparent',

View File

@@ -36,6 +36,10 @@ class FoxNewsIE(AMPIE):
# 'upload_date': '20141204',
'thumbnail': 're:^https?://.*\.jpg$',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',

View File

@@ -10,7 +10,7 @@ class FranceInterIE(InfoExtractor):
_TEST = {
'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
'md5': '4764932e466e6f6c79c317d2e74f6884',
"info_dict": {
'info_dict': {
'id': '793962',
'ext': 'mp3',
'title': 'LHistoire dans les jeux vidéo',

View File

@@ -289,7 +289,7 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_id, catalogue = self._html_search_regex(
r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
webpage, 'video ID').split('@')
return self._extract_video(video_id, catalogue)

View File

@@ -14,7 +14,7 @@ class FreespeechIE(InfoExtractor):
'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0',
'info_dict': {
'id': 'poKsVCZ64uU',
'ext': 'mp4',
'ext': 'webm',
'title': 'Obama, Romney Campaign in Colorado Ahead of Debate',
'description': 'Obama, Romney Campaign in Colorado Ahead of Debate',
'uploader': 'freespeechtv',

View File

@@ -12,8 +12,8 @@ class FreeVideoIE(InfoExtractor):
'info_dict': {
'id': 'vysukany-zadecek-22033',
'ext': 'mp4',
"title": "vysukany-zadecek-22033",
"age_limit": 18,
'title': 'vysukany-zadecek-22033',
'age_limit': 18,
},
'skip': 'Blocked outside .cz',
}

View File

@@ -6,24 +6,29 @@ from ..utils import (
xpath_text,
xpath_with_ns,
)
from .youtube import YoutubeIE
class GamekingsIE(InfoExtractor):
_VALID_URL = r'http://www\.gamekings\.tv/(?:videos|nieuws)/(?P<id>[^/]+)'
_VALID_URL = r'http://www\.gamekings\.nl/(?:videos|nieuws)/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
# MD5 is flaky, seems to change regularly
# 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3',
# YouTube embed video
'url': 'http://www.gamekings.nl/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
'md5': '5208d3a17adeaef829a7861887cb9029',
'info_dict': {
'id': 'phoenix-wright-ace-attorney-dual-destinies-review',
'id': 'HkSQKetlGOU',
'ext': 'mp4',
'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review',
'description': 'md5:36fd701e57e8c15ac8682a2374c99731',
'title': 'Phoenix Wright: Ace Attorney - Dual Destinies Review',
'description': 'md5:db88c0e7f47e9ea50df3271b9dc72e1d',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader_id': 'UCJugRGo4STYMeFr5RoOShtQ',
'uploader': 'Gamekings Vault',
'upload_date': '20151123',
},
'add_ie': ['Youtube'],
}, {
# vimeo video
'url': 'http://www.gamekings.tv/videos/the-legend-of-zelda-majoras-mask/',
'url': 'http://www.gamekings.nl/videos/the-legend-of-zelda-majoras-mask/',
'md5': '12bf04dfd238e70058046937657ea68d',
'info_dict': {
'id': 'the-legend-of-zelda-majoras-mask',
@@ -33,7 +38,7 @@ class GamekingsIE(InfoExtractor):
'thumbnail': 're:^https?://.*\.jpg$',
},
}, {
'url': 'http://www.gamekings.tv/nieuws/gamekings-extra-shelly-en-david-bereiden-zich-voor-op-de-livestream/',
'url': 'http://www.gamekings.nl/nieuws/gamekings-extra-shelly-en-david-bereiden-zich-voor-op-de-livestream/',
'only_matching': True,
}]
@@ -43,7 +48,11 @@ class GamekingsIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
playlist_id = self._search_regex(
r'gogoVideo\(\s*\d+\s*,\s*"([^"]+)', webpage, 'playlist id')
r'gogoVideo\([^,]+,\s*"([^"]+)', webpage, 'playlist id')
# Check if a YouTube embed is used
if YoutubeIE.suitable(playlist_id):
return self.url_result(playlist_id, ie='Youtube')
playlist = self._download_xml(
'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=%s' % playlist_id,

View File

@@ -47,6 +47,7 @@ from .senateisvp import SenateISVPIE
from .svt import SVTIE
from .pornhub import PornHubIE
from .xhamster import XHamsterEmbedIE
from .tnaflix import TNAFlixNetworkEmbedIE
from .vimeo import VimeoIE
from .dailymotion import DailymotionCloudIE
from .onionstudios import OnionStudiosIE
@@ -57,7 +58,7 @@ from .pladform import PladformIE
from .videomore import VideomoreIE
from .googledrive import GoogleDriveIE
from .jwplatform import JWPlatformIE
from .ultimedia import UltimediaIE
from .digiteka import DigitekaIE
class GenericIE(InfoExtractor):
@@ -224,6 +225,20 @@ class GenericIE(InfoExtractor):
'skip_download': True,
},
},
# MPD from http://dash-mse-test.appspot.com/media.html
{
'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
'info_dict': {
'id': 'car-20120827-manifest',
'ext': 'mp4',
'title': 'car-20120827-manifest',
'formats': 'mincount:9',
},
'params': {
'format': 'bestvideo',
},
},
# google redirect
{
'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
@@ -1229,19 +1244,24 @@ class GenericIE(InfoExtractor):
# Check for direct link to a video
content_type = head_response.headers.get('Content-Type', '')
m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
if m:
upload_date = unified_strdate(
head_response.headers.get('Last-Modified'))
formats = []
if m.group('format_id').endswith('mpegurl'):
formats = self._extract_m3u8_formats(url, video_id, 'mp4')
else:
formats = [{
'format_id': m.group('format_id'),
'url': url,
'vcodec': 'none' if m.group('type') == 'audio' else None
}]
return {
'id': video_id,
'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
'direct': True,
'formats': [{
'format_id': m.group('format_id'),
'url': url,
'vcodec': 'none' if m.group('type') == 'audio' else None
}],
'formats': formats,
'upload_date': upload_date,
}
@@ -1284,7 +1304,7 @@ class GenericIE(InfoExtractor):
self.report_extraction(video_id)
# Is it an RSS feed, a SMIL file or a XSPF playlist?
# Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
try:
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
@@ -1293,6 +1313,13 @@ class GenericIE(InfoExtractor):
return self._parse_smil(doc, url, video_id)
elif doc.tag == '{http://xspf.org/ns/0/}playlist':
return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
return {
'id': video_id,
'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
'formats': self._parse_mpd_formats(
doc, video_id, mpd_base_url=url.rpartition('/')[0]),
}
except compat_xml_parse_error:
pass
@@ -1402,7 +1429,7 @@ class GenericIE(InfoExtractor):
# Look for embedded Dailymotion player
matches = re.findall(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
if matches:
return _playlist_from_matches(
matches, lambda m: unescapeHTML(m[1]))
@@ -1547,6 +1574,11 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(mobj.group('url'), 'VK')
# Look for embedded Odnoklassniki player
mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Odnoklassniki')
# Look for embedded ivi player
mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
if mobj is not None:
@@ -1602,6 +1634,11 @@ class GenericIE(InfoExtractor):
if xhamster_urls:
return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
# Look for embedded TNAFlixNetwork player
tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
if tnaflix_urls:
return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
# Look for embedded Tvigle player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
@@ -1814,10 +1851,21 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
# Look for Ulltimedia embeds
ultimedia_url = UltimediaIE._extract_url(webpage)
if ultimedia_url:
return self.url_result(self._proto_relative_url(ultimedia_url), 'Ultimedia')
# Look for Digiteka embeds
digiteka_url = DigitekaIE._extract_url(webpage)
if digiteka_url:
return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
# Look for Limelight embeds
mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
if mobj:
lm = {
'Media': 'media',
'Channel': 'channel',
'ChannelList': 'channel_list',
}
return self.url_result('limelight:%s:%s' % (
lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
# Look for AdobeTVVideo embeds
mobj = re.search(
@@ -1935,6 +1983,8 @@ class GenericIE(InfoExtractor):
return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
elif ext == 'm3u8':
entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
elif ext == 'mpd':
entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
else:
entry_info_dict['url'] = video_url

View File

@@ -65,7 +65,7 @@ class GloboIE(InfoExtractor):
'only_matching': True,
}]
class MD5:
class MD5(object):
HEX_FORMAT_LOWERCASE = 0
HEX_FORMAT_UPPERCASE = 1
BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = ''

View File

@@ -82,7 +82,7 @@ class GoogleDriveIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'duration': duration,
'formats': formats,
}

View File

@@ -11,8 +11,8 @@ class HentaiStigmaIE(InfoExtractor):
'info_dict': {
'id': 'inyouchuu-etsu-bonus',
'ext': 'mp4',
"title": "Inyouchuu Etsu Bonus",
"age_limit": 18,
'title': 'Inyouchuu Etsu Bonus',
'age_limit': 18,
}
}

View File

@@ -159,6 +159,9 @@ class HitboxLiveIE(HitboxIE):
cdns = player_config.get('cdns')
servers = []
for cdn in cdns:
# Subscribe URLs are not playable
if cdn.get('rtmpSubscribe') is True:
continue
base_url = cdn.get('netConnectionUrl')
host = re.search('.+\.([^\.]+\.[^\./]+)/.+', base_url).group(1)
if base_url not in servers:

View File

@@ -10,8 +10,8 @@ from ..utils import (
class HotStarIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hotstar\.com/.*?[/-](?P<id>\d{10})'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
_TESTS = [{
'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
'info_dict': {
'id': '1000076273',
@@ -26,7 +26,13 @@ class HotStarIE(InfoExtractor):
# m3u8 download
'skip_download': True,
}
}
}, {
'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583',
'only_matching': True,
}, {
'url': 'http://www.hotstar.com/1000000515',
'only_matching': True,
}]
_GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s'
_GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s'

View File

@@ -42,7 +42,7 @@ class ImdbIE(InfoExtractor):
for f_url, f_name in extra_formats]
format_pages.append(player_page)
quality = qualities(['SD', '480p', '720p'])
quality = qualities(('SD', '480p', '720p', '1080p'))
formats = []
for format_page in format_pages:
json_data = self._search_regex(

View File

@@ -73,7 +73,7 @@ class IndavideoEmbedIE(InfoExtractor):
'url': self._proto_relative_url(thumbnail)
} for thumbnail in video.get('thumbnails', [])]
tags = [tag['title'] for tag in video.get('tags', [])]
tags = [tag['title'] for tag in video.get('tags') or []]
return {
'id': video.get('id') or video_id,

View File

@@ -4,15 +4,12 @@ from __future__ import unicode_literals
import base64
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
compat_parse_qs,
)
from ..compat import compat_urllib_parse_unquote
from ..utils import determine_ext
from .bokecc import BokeCCBaseIE
class InfoQIE(InfoExtractor):
class InfoQIE(BokeCCBaseIE):
_VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)'
_TESTS = [{
@@ -38,26 +35,6 @@ class InfoQIE(InfoExtractor):
},
}]
def _extract_bokecc_videos(self, webpage, video_id):
# TODO: bokecc.com is a Chinese video cloud platform
# It should have an independent extractor but I don't have other
# examples using bokecc
player_params_str = self._html_search_regex(
r'<script[^>]+src="http://p\.bokecc\.com/player\?([^"]+)',
webpage, 'player params', default=None)
player_params = compat_parse_qs(player_params_str)
info_xml = self._download_xml(
'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % (
player_params['siteid'][0], player_params['vid'][0]), video_id)
return [{
'format_id': 'bokecc',
'url': quality.find('./copy').attrib['playurl'],
'preference': int(quality.attrib['value']),
} for quality in info_xml.findall('./video/quality')]
def _extract_rtmp_videos(self, webpage):
# The server URL is hardcoded
video_url = 'rtmpe://video.infoq.com/cfx/st/'
@@ -101,7 +78,7 @@ class InfoQIE(InfoExtractor):
if '/cn/' in url:
# for China videos, HTTP video URL exists but always fails with 403
formats = self._extract_bokecc_videos(webpage, video_id)
formats = self._extract_bokecc_formats(webpage, video_id)
else:
formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage)

View File

@@ -21,6 +21,18 @@ class InstagramIE(InfoExtractor):
'title': 'Video by naomipq',
'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
}
}, {
# missing description
'url': 'https://www.instagram.com/p/BA-pQFBG8HZ/?taken-by=britneyspears',
'info_dict': {
'id': 'BA-pQFBG8HZ',
'ext': 'mp4',
'uploader_id': 'britneyspears',
'title': 'Video by britneyspears',
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://instagram.com/p/-Cmh1cukG2/',
'only_matching': True,
@@ -32,8 +44,8 @@ class InstagramIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
webpage, 'uploader id', fatal=False)
desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description',
fatal=False)
desc = self._search_regex(
r'"caption":"(.+?)"', webpage, 'description', default=None)
return {
'id': video_id,

View File

@@ -2,46 +2,30 @@
from __future__ import unicode_literals
import re
from random import random
from math import floor
import time
from .common import InfoExtractor
from ..utils import (
ExtractorError,
remove_end,
sanitized_Request,
)
class IPrimaIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'
_VALID_URL = r'https?://play\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
_TESTS = [{
'url': 'http://play.iprima.cz/gondici-s-r-o-33',
'info_dict': {
'id': 'p136534',
'ext': 'mp4',
'title': 'Gondíci s. r. o. (34)',
'description': 'md5:16577c629d006aa91f59ca8d8e7f99bd',
},
'params': {
'skip_download': True, # m3u8 download
},
}, {
'url': 'http://play.iprima.cz/particka/particka-92',
'info_dict': {
'id': '39152',
'ext': 'flv',
'title': 'Partička (92)',
'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45',
'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
},
'params': {
'skip_download': True, # requires rtmpdump
},
}, {
'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda',
'info_dict': {
'id': '9718337',
'ext': 'flv',
'title': 'Tchibo Partička - Jarní móda',
'thumbnail': 're:^http:.*\.jpg$',
},
'params': {
'skip_download': True, # requires rtmpdump
},
}, {
'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015',
'only_matching': True,
}]
@@ -51,62 +35,24 @@ class IPrimaIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
if re.search(r'Nemáte oprávnění přistupovat na tuto stránku\.\s*</div>', webpage):
raise ExtractorError(
'%s said: You do not have permission to access this page' % self.IE_NAME, expected=True)
video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id')
player_url = (
'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' %
(floor(random() * 1073741824), floor(random() * 1073741824))
)
req = sanitized_Request(player_url)
req = sanitized_Request(
'http://play.iprima.cz/prehravac/init?_infuse=1'
'&_ts=%s&productId=%s' % (round(time.time()), video_id))
req.add_header('Referer', url)
playerpage = self._download_webpage(req, video_id)
playerpage = self._download_webpage(req, video_id, note='Downloading player')
base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
m3u8_url = self._search_regex(r"'src': '([^']+\.m3u8)'", playerpage, 'm3u8 url')
zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
if zoneGEO != '0':
base_url = base_url.replace('token', 'token_' + zoneGEO)
formats = []
for format_id in ['lq', 'hq', 'hd']:
filename = self._html_search_regex(
r'"%s_id":(.+?),' % format_id, webpage, 'filename')
if filename == 'null':
continue
real_id = self._search_regex(
r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]',
filename, 'real video id')
if format_id == 'lq':
quality = 0
elif format_id == 'hq':
quality = 1
elif format_id == 'hd':
quality = 2
filename = 'hq/' + filename
formats.append({
'format_id': format_id,
'url': base_url,
'quality': quality,
'play_path': 'mp4:' + filename.replace('"', '')[:-4],
'rtmp_live': True,
'ext': 'flv',
})
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
self._sort_formats(formats)
return {
'id': real_id,
'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'),
'id': video_id,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
'description': self._search_regex(
r'<p[^>]+itemprop="description"[^>]*>([^<]+)',
webpage, 'description', default=None),
'description': self._og_search_description(webpage),
}

View File

@@ -2,14 +2,163 @@
from __future__ import unicode_literals
import hashlib
import itertools
import math
import os
import random
import re
import time
import uuid
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..utils import ExtractorError
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse,
compat_urllib_parse_urlparse,
)
from ..utils import (
decode_packed_codes,
ExtractorError,
ohdave_rsa_encrypt,
remove_start,
sanitized_Request,
urlencode_postdata,
url_basename,
)
def md5_text(text):
return hashlib.md5(text.encode('utf-8')).hexdigest()
class IqiyiSDK(object):
def __init__(self, target, ip, timestamp):
self.target = target
self.ip = ip
self.timestamp = timestamp
@staticmethod
def split_sum(data):
return compat_str(sum(map(lambda p: int(p, 16), list(data))))
@staticmethod
def digit_sum(num):
if isinstance(num, int):
num = compat_str(num)
return compat_str(sum(map(int, num)))
def even_odd(self):
even = self.digit_sum(compat_str(self.timestamp)[::2])
odd = self.digit_sum(compat_str(self.timestamp)[1::2])
return even, odd
def preprocess(self, chunksize):
self.target = md5_text(self.target)
chunks = []
for i in range(32 // chunksize):
chunks.append(self.target[chunksize * i:chunksize * (i + 1)])
if 32 % chunksize:
chunks.append(self.target[32 - 32 % chunksize:])
return chunks, list(map(int, self.ip.split('.')))
def mod(self, modulus):
chunks, ip = self.preprocess(32)
self.target = chunks[0] + ''.join(map(lambda p: compat_str(p % modulus), ip))
def split(self, chunksize):
modulus_map = {
4: 256,
5: 10,
8: 100,
}
chunks, ip = self.preprocess(chunksize)
ret = ''
for i in range(len(chunks)):
ip_part = compat_str(ip[i] % modulus_map[chunksize]) if i < 4 else ''
if chunksize == 8:
ret += ip_part + chunks[i]
else:
ret += chunks[i] + ip_part
self.target = ret
def handle_input16(self):
self.target = md5_text(self.target)
self.target = self.split_sum(self.target[:16]) + self.target + self.split_sum(self.target[16:])
def handle_input8(self):
self.target = md5_text(self.target)
ret = ''
for i in range(4):
part = self.target[8 * i:8 * (i + 1)]
ret += self.split_sum(part) + part
self.target = ret
def handleSum(self):
self.target = md5_text(self.target)
self.target = self.split_sum(self.target) + self.target
def date(self, scheme):
self.target = md5_text(self.target)
d = time.localtime(self.timestamp)
strings = {
'y': compat_str(d.tm_year),
'm': '%02d' % d.tm_mon,
'd': '%02d' % d.tm_mday,
}
self.target += ''.join(map(lambda c: strings[c], list(scheme)))
def split_time_even_odd(self):
even, odd = self.even_odd()
self.target = odd + md5_text(self.target) + even
def split_time_odd_even(self):
even, odd = self.even_odd()
self.target = even + md5_text(self.target) + odd
def split_ip_time_sum(self):
chunks, ip = self.preprocess(32)
self.target = compat_str(sum(ip)) + chunks[0] + self.digit_sum(self.timestamp)
def split_time_ip_sum(self):
chunks, ip = self.preprocess(32)
self.target = self.digit_sum(self.timestamp) + chunks[0] + compat_str(sum(ip))
class IqiyiSDKInterpreter(object):
def __init__(self, sdk_code):
self.sdk_code = sdk_code
def run(self, target, ip, timestamp):
self.sdk_code = decode_packed_codes(self.sdk_code)
functions = re.findall(r'input=([a-zA-Z0-9]+)\(input', self.sdk_code)
sdk = IqiyiSDK(target, ip, timestamp)
other_functions = {
'handleSum': sdk.handleSum,
'handleInput8': sdk.handle_input8,
'handleInput16': sdk.handle_input16,
'splitTimeEvenOdd': sdk.split_time_even_odd,
'splitTimeOddEven': sdk.split_time_odd_even,
'splitIpTimeSum': sdk.split_ip_time_sum,
'splitTimeIpSum': sdk.split_time_ip_sum,
}
for function in functions:
if re.match(r'mod\d+', function):
sdk.mod(int(function[3:]))
elif re.match(r'date[ymd]{3}', function):
sdk.date(function[4:])
elif re.match(r'split\d+', function):
sdk.split(int(function[5:]))
elif function in other_functions:
other_functions[function]()
else:
raise ExtractorError('Unknown funcion %s' % function)
return sdk.target
class IqiyiIE(InfoExtractor):
@@ -18,6 +167,8 @@ class IqiyiIE(InfoExtractor):
_VALID_URL = r'http://(?:[^.]+\.)?iqiyi\.com/.+\.html'
_NETRC_MACHINE = 'iqiyi'
_TESTS = [{
'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
'md5': '2cb594dc2781e6c941a110d8f358118b',
@@ -93,6 +244,35 @@ class IqiyiIE(InfoExtractor):
}, {
'url': 'http://yule.iqiyi.com/pcb.html',
'only_matching': True,
}, {
# VIP-only video. The first 2 parts (6 minutes) are available without login
# MD5 sums omitted as values are different on Travis CI and my machine
'url': 'http://www.iqiyi.com/v_19rrny4w8w.html',
'info_dict': {
'id': 'f3cf468b39dddb30d676f89a91200dc1',
'title': '泰坦尼克号',
},
'playlist': [{
'info_dict': {
'id': 'f3cf468b39dddb30d676f89a91200dc1_part1',
'ext': 'f4v',
'title': '泰坦尼克号',
},
}, {
'info_dict': {
'id': 'f3cf468b39dddb30d676f89a91200dc1_part2',
'ext': 'f4v',
'title': '泰坦尼克号',
},
}],
'expected_warnings': ['Needs a VIP account for full video'],
}, {
'url': 'http://www.iqiyi.com/a_19rrhb8ce1.html',
'info_dict': {
'id': '202918101',
'title': '灌篮高手 国语版',
},
'playlist_count': 101,
}]
_FORMATS_MAP = [
@@ -104,11 +284,98 @@ class IqiyiIE(InfoExtractor):
('10', 'h1'),
]
@staticmethod
def md5_text(text):
return hashlib.md5(text.encode('utf-8')).hexdigest()
def _real_initialize(self):
self._login()
def construct_video_urls(self, data, video_id, _uuid):
@staticmethod
def _rsa_fun(data):
# public key extracted from http://static.iqiyi.com/js/qiyiV2/20160129180840/jobs/i18n/i18nIndex.js
N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
e = 65537
return ohdave_rsa_encrypt(data, e, N)
def _login(self):
(username, password) = self._get_login_info()
# No authentication to be performed
if not username:
return True
data = self._download_json(
'http://kylin.iqiyi.com/get_token', None,
note='Get token for logging', errnote='Unable to get token for logging')
sdk = data['sdk']
timestamp = int(time.time())
target = '/apis/reglogin/login.action?lang=zh_TW&area_code=null&email=%s&passwd=%s&agenttype=1&from=undefined&keeplogin=0&piccode=&fromurl=&_pos=1' % (
username, self._rsa_fun(password.encode('utf-8')))
interp = IqiyiSDKInterpreter(sdk)
sign = interp.run(target, data['ip'], timestamp)
validation_params = {
'target': target,
'server': 'BEA3AA1908656AABCCFF76582C4C6660',
'token': data['token'],
'bird_src': 'f8d91d57af224da7893dd397d52d811a',
'sign': sign,
'bird_t': timestamp,
}
validation_result = self._download_json(
'http://kylin.iqiyi.com/validate?' + compat_urllib_parse.urlencode(validation_params), None,
note='Validate credentials', errnote='Unable to validate credentials')
MSG_MAP = {
'P00107': 'please login via the web interface and enter the CAPTCHA code',
'P00117': 'bad username or password',
}
code = validation_result['code']
if code != 'A00000':
msg = MSG_MAP.get(code)
if not msg:
msg = 'error %s' % code
if validation_result.get('msg'):
msg += ': ' + validation_result['msg']
self._downloader.report_warning('unable to log in: ' + msg)
return False
return True
def _authenticate_vip_video(self, api_video_url, video_id, tvid, _uuid, do_report_warning):
auth_params = {
# version and platform hard-coded in com/qiyi/player/core/model/remote/AuthenticationRemote.as
'version': '2.0',
'platform': 'b6c13e26323c537d',
'aid': tvid,
'tvid': tvid,
'uid': '',
'deviceId': _uuid,
'playType': 'main', # XXX: always main?
'filename': os.path.splitext(url_basename(api_video_url))[0],
}
qd_items = compat_parse_qs(compat_urllib_parse_urlparse(api_video_url).query)
for key, val in qd_items.items():
auth_params[key] = val[0]
auth_req = sanitized_Request(
'http://api.vip.iqiyi.com/services/ckn.action',
urlencode_postdata(auth_params))
# iQiyi server throws HTTP 405 error without the following header
auth_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
auth_result = self._download_json(
auth_req, video_id,
note='Downloading video authentication JSON',
errnote='Unable to download video authentication JSON')
if auth_result['code'] == 'Q00506': # requires a VIP account
if do_report_warning:
self.report_warning('Needs a VIP account for full video')
return False
return auth_result
def construct_video_urls(self, data, video_id, _uuid, tvid):
def do_xor(x, y):
a = y % 3
if a == 1:
@@ -134,9 +401,10 @@ class IqiyiIE(InfoExtractor):
note='Download path key of segment %d for format %s' % (segment_index + 1, format_id)
)['t']
t = str(int(math.floor(int(tm) / (600.0))))
return self.md5_text(t + mg + x)
return md5_text(t + mg + x)
video_urls_dict = {}
need_vip_warning_report = True
for format_item in data['vp']['tkl'][0]['vs']:
if 0 < int(format_item['bid']) <= 10:
format_id = self.get_format(format_item['bid'])
@@ -155,11 +423,13 @@ class IqiyiIE(InfoExtractor):
vl = segment['l']
if not vl.startswith('/'):
vl = get_encode_code(vl)
key = get_path_key(
vl.split('/')[-1].split('.')[0], format_id, segment_index)
is_vip_video = '/vip/' in vl
filesize = segment['b']
base_url = data['vp']['du'].split('/')
base_url.insert(-1, key)
if not is_vip_video:
key = get_path_key(
vl.split('/')[-1].split('.')[0], format_id, segment_index)
base_url.insert(-1, key)
base_url = '/'.join(base_url)
param = {
'su': _uuid,
@@ -170,8 +440,23 @@ class IqiyiIE(InfoExtractor):
'ct': '',
'tn': str(int(time.time()))
}
api_video_url = base_url + vl + '?' + \
compat_urllib_parse.urlencode(param)
api_video_url = base_url + vl
if is_vip_video:
api_video_url = api_video_url.replace('.f4v', '.hml')
auth_result = self._authenticate_vip_video(
api_video_url, video_id, tvid, _uuid, need_vip_warning_report)
if auth_result is False:
need_vip_warning_report = False
break
param.update({
't': auth_result['data']['t'],
# cid is hard-coded in com/qiyi/player/core/player/RuntimeData.as
'cid': 'afbe8fd3d73448c9',
'vid': video_id,
'QY00001': auth_result['data']['u'],
})
api_video_url += '?' if '?' not in api_video_url else '&'
api_video_url += compat_urllib_parse.urlencode(param)
js = self._download_json(
api_video_url, video_id,
note='Download video info of segment %d for format %s' % (segment_index + 1, format_id))
@@ -195,16 +480,17 @@ class IqiyiIE(InfoExtractor):
tail = tm + tvid
param = {
'key': 'fvip',
'src': self.md5_text('youtube-dl'),
'src': md5_text('youtube-dl'),
'tvId': tvid,
'vid': video_id,
'vinfo': 1,
'tm': tm,
'enc': self.md5_text(enc_key + tail),
'enc': md5_text(enc_key + tail),
'qyid': _uuid,
'tn': random.random(),
'um': 0,
'authkey': self.md5_text(self.md5_text('') + tail),
'authkey': md5_text(md5_text('') + tail),
'k_tag': 1,
}
api_url = 'http://cache.video.qiyi.com/vms' + '?' + \
@@ -212,40 +498,75 @@ class IqiyiIE(InfoExtractor):
raw_data = self._download_json(api_url, video_id)
return raw_data
def get_enc_key(self, swf_url, video_id):
def get_enc_key(self, video_id):
# TODO: automatic key extraction
# last update at 2015-12-18 for Zombie::bite
enc_key = '8b6b683780897eb8d9a48a02ccc4817d'[::-1]
# last update at 2016-01-22 for Zombie::bite
enc_key = '6ab6d0280511493ba85594779759d4ed'
return enc_key
def _extract_playlist(self, webpage):
PAGE_SIZE = 50
links = re.findall(
r'<a[^>]+class="site-piclist_pic_link"[^>]+href="(http://www\.iqiyi\.com/.+\.html)"',
webpage)
if not links:
return
album_id = self._search_regex(
r'albumId\s*:\s*(\d+),', webpage, 'album ID')
album_title = self._search_regex(
r'data-share-title="([^"]+)"', webpage, 'album title', fatal=False)
entries = list(map(self.url_result, links))
# Start from 2 because links in the first page are already on webpage
for page_num in itertools.count(2):
pagelist_page = self._download_webpage(
'http://cache.video.qiyi.com/jp/avlist/%s/%d/%d/' % (album_id, page_num, PAGE_SIZE),
album_id,
note='Download playlist page %d' % page_num,
errnote='Failed to download playlist page %d' % page_num)
pagelist = self._parse_json(
remove_start(pagelist_page, 'var tvInfoJs='), album_id)
vlist = pagelist['data']['vlist']
for item in vlist:
entries.append(self.url_result(item['vurl']))
if len(vlist) < PAGE_SIZE:
break
return self.playlist_result(entries, album_id, album_title)
def _real_extract(self, url):
webpage = self._download_webpage(
url, 'temp_id', note='download video page')
# There's no simple way to determine whether an URL is a playlist or not
# So detect it
playlist_result = self._extract_playlist(webpage)
if playlist_result:
return playlist_result
tvid = self._search_regex(
r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid')
video_id = self._search_regex(
r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
swf_url = self._search_regex(
r'(http://[^\'"]+MainPlayer[^.]+\.swf)', webpage, 'swf player URL')
_uuid = uuid.uuid4().hex
enc_key = self.get_enc_key(swf_url, video_id)
enc_key = self.get_enc_key(video_id)
raw_data = self.get_raw_data(tvid, video_id, enc_key, _uuid)
if raw_data['code'] != 'A000000':
raise ExtractorError('Unable to load data. Error code: ' + raw_data['code'])
if not raw_data['data']['vp']['tkl']:
raise ExtractorError('No support iQiqy VIP video')
data = raw_data['data']
title = data['vi']['vn']
# generate video_urls_dict
video_urls_dict = self.construct_video_urls(
data, video_id, _uuid)
data, video_id, _uuid, tvid)
# construct info
entries = []

View File

@@ -30,7 +30,7 @@ class JeuxVideoIE(InfoExtractor):
webpage = self._download_webpage(url, title)
title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
config_url = self._html_search_regex(
r'data-src="(/contenu/medias/video.php.*?)"',
r'data-src(?:set-video)?="(/contenu/medias/video.php.*?)"',
webpage, 'config URL')
config_url = 'http://www.jeuxvideo.com' + config_url

View File

@@ -7,7 +7,46 @@ from .common import InfoExtractor
from ..utils import int_or_none
class JWPlatformIE(InfoExtractor):
class JWPlatformBaseIE(InfoExtractor):
def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True):
video_data = jwplayer_data['playlist'][0]
subtitles = {}
for track in video_data['tracks']:
if track['kind'] == 'captions':
subtitles[track['label']] = [{'url': self._proto_relative_url(track['file'])}]
formats = []
for source in video_data['sources']:
source_url = self._proto_relative_url(source['file'])
source_type = source.get('type') or ''
if source_type in ('application/vnd.apple.mpegurl', 'hls'):
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', 'm3u8_native', fatal=False))
elif source_type.startswith('audio'):
formats.append({
'url': source_url,
'vcodec': 'none',
})
else:
formats.append({
'url': source_url,
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': video_data['title'] if require_title else video_data.get('title'),
'description': video_data.get('description'),
'thumbnail': self._proto_relative_url(video_data.get('image')),
'timestamp': int_or_none(video_data.get('pubdate')),
'subtitles': subtitles,
'formats': formats,
}
class JWPlatformIE(JWPlatformBaseIE):
_VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
_TEST = {
'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
@@ -33,38 +72,4 @@ class JWPlatformIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id)
video_data = json_data['playlist'][0]
subtitles = {}
for track in video_data['tracks']:
if track['kind'] == 'captions':
subtitles[track['label']] = [{'url': self._proto_relative_url(track['file'])}]
formats = []
for source in video_data['sources']:
source_url = self._proto_relative_url(source['file'])
source_type = source.get('type') or ''
if source_type == 'application/vnd.apple.mpegurl':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', 'm3u8_native', fatal=False))
elif source_type.startswith('audio'):
formats.append({
'url': source_url,
'vcodec': 'none',
})
else:
formats.append({
'url': source_url,
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': video_data['title'],
'description': video_data.get('description'),
'thumbnail': self._proto_relative_url(video_data.get('image')),
'timestamp': int_or_none(video_data.get('pubdate')),
'subtitles': subtitles,
'formats': formats,
}
return self._parse_jwplayer_data(json_data, video_id)

Some files were not shown because too many files have changed in this diff Show More